© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11981
    Prev
    Next
    INDEX
    Explanations

    words ending in "table" or related to legal reporting requirements

    oai_token-act-pair · gemini-2.0-flash

    reports and disclosures

    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
    Not in Any Lists

    No Comments

    Negative Logits
    kształ
    -0.53
    erai
    -0.53
    ClientSize
    -0.52
     stir
    -0.51
     useParams
    -0.50
     ň
    -0.50
    CPtr
    -0.50
    baix
    -0.49
    ViewChild
    -0.48
    ➟
    -0.48
    POSITIVE LOGITS
    BibitemShut
    0.56
    WebVitals
    0.54
    ſelf
    0.53
    fillType
    0.51
    ſelves
    0.48
    HtmlAttribute
    0.46
     commentaire
    0.46
    intios
    0.45
    moveToFirst
    0.45
     themſelves
    0.45
    Activations Density 1.504%

    No Known Activations