© 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. 13552
    Prev
    Next
    INDEX
    Explanations

    references to formal announcements

    oai_token-act-pair · gemini-2.0-flash

    statement

    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
    Jeografia
    -0.60
    tagHelperRunner
    -0.59
    országban
    -0.54
    oa̍t
    -0.54
    SourceChecksum
    -0.52
     Signalez
    -0.50
    simile
    -0.48
     activado
    -0.48
     bá
    -0.46
    urably
    -0.46
    POSITIVE LOGITS
    bootstrapcdn
    0.76
     AttributeSet
    0.52
    announced
    0.51
    ниш
    0.51
     SqlCommand
    0.50
    راسیون
    0.49
    tidine
    0.49
    Brief
    0.48
    方がいい
    0.47
    erapeu
    0.47
    Activations Density 0.723%

    No Known Activations