© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9445
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols, particularly within research paper notation.

    oai_token-act-pair · gemini-2.0-flash

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ''
    -0.56
     unknownFields
    -0.56
    出版年
    -0.53
     ra
    -0.49
    <bos>
    -0.48
    quot
    -0.48
    icorn
    -0.47
    </em>
    -0.47
     ”
    -0.47
     St
    -0.45
    POSITIVE LOGITS
     виправивши
    0.79
    ArgsConstructor
    0.78
    DockStyle
    0.75
     propOrder
    0.73
     itſelf
    0.71
     BorderSide
    0.70
    +#+#
    0.69
     doubtnut
    0.67
     BoxFit
    0.66
    extAlignment
    0.64
    Activations Density 2.573%

    No Known Activations