© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14600
    Prev
    Next
    INDEX
    Explanations

    words related to stories and characters

    oai_token-act-pair · gemini-2.0-flash

    character

    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
    Not in Any Lists

    No Comments

    Negative Logits
    prefixer
    -0.53
    matite
    -0.49
     financière
    -0.49
     oph
    -0.48
    hynch
    -0.46
     financiero
    -0.44
    span
    -0.44
    mappedBy
    -0.43
    div
    -0.43
    Periods
    -0.43
    POSITIVE LOGITS
     незавершена
    0.60
    qrstuvwxyz
    0.59
    ">//
    0.58
     Bod
    0.58
    UrlResolution
    0.57
    ształ
    0.57
    TypedDataSet
    0.57
    Portale
    0.57
     متعلقه
    0.56
    unzel
    0.56
    Activations Density 1.546%

    No Known Activations