© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14117
    Prev
    Next
    INDEX
    Explanations

    strings of letters that might be found in scientific writing, possibly related to citations or chemical formulas

    oai_token-act-pair · gemini-2.0-flash

    Scientific documents

    np_max-act · gemini-2.0-flash

    say "punctuation" Method used: 2 — because following tokens are punctuation/symbols — say "punctuation"

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DoubleQuotes
    -0.73
    numerusform
    -0.70
    ArgsConstructor
    -0.66
     
    -0.65
    HasForeignKey
    -0.65
     متعلقه
    -0.64
    thenReturn
    -0.64
     BoxFit
    -0.63
    utory
    -0.60
    randomUUID
    -0.59
    POSITIVE LOGITS
    <bos>
    1.58
    '
    0.61
    érfi
    0.46
    исленность
    0.46
     negociación
    0.45
    enschein
    0.45
     scrittura
    0.45
     Umgang
    0.44
     himſelf
    0.44
     iluminação
    0.44
    Activations Density 1.491%

    No Known Activations