© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12413
    Prev
    Next
    INDEX
    Explanations

    various terms from programming languages, libraries, and mathematics

    oai_token-act-pair · gemini-2.0-flash

    programming and PDF forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    NewLabel
    -0.69
    <bos>
    -0.64
     Wicidata
    -0.59
    хьтан
    -0.58
    StreetMap
    -0.57
     Anſ
    -0.56
    noopener
    -0.55
    iffance
    -0.52
     spannend
    -0.52
     auffi
    -0.52
    POSITIVE LOGITS
     Normdatei
    0.69
     esternos
    0.67
    EndContext
    0.67
    RenderAtEndOf
    0.63
    ArgsConstructor
    0.63
     سكانية
    0.61
     Penh
    0.60
    rungsseite
    0.60
    ]")]
    0.60
     Audiodateien
    0.59
    Activations Density 10.773%

    No Known Activations