© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13749
    Prev
    Next
    INDEX
    Explanations

    numerical data and study IDs.

    oai_token-act-pair · gemini-2.0-flash

    disorganized data

    np_max-act · gemini-2.0-flash

    ▁ Method used: 1 — because all max-activating entries are the same leading-space subword marker — ▁

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.79
    ArgsConstructor
    -0.78
    DoubleQuotes
    -0.67
     الحره
    -0.66
     MainAxisSize
    -0.66
    出版年
    -0.61
     surla
    -0.59
    ثيق
    -0.58
    tagHelperRunner
    -0.57
     ujednoznacz
    -0.56
    POSITIVE LOGITS
    <bos>
    0.81
     Efq
    0.52
    — 
    0.49
     Theſe
    0.49
    ítulos
    0.49
     Monfieur
    0.48
     Ganze
    0.47
    modb
    0.47
    The
    0.46
     caliente
    0.46
    Activations Density 1.492%

    No Known Activations