© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9016
    Prev
    Next
    INDEX
    Explanations

    descriptive language involving color, appearance, and assembly

    oai_token-act-pair · gemini-2.0-flash

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     estekak
    -0.60
    <bos>
    -0.46
    lielmo
    -0.46
    Origin
    -0.45
    вич
    -0.43
    Handlung
    -0.43
    負
    -0.43
     Origin
    -0.42
    ائ
    -0.42
    원
    -0.42
    POSITIVE LOGITS
    TypedDataSet
    0.70
    principalColumn
    0.67
    aarrggbb
    0.61
     prohibido
    0.58
    HasAnnotation
    0.56
    afficheront
    0.56
    <tfoot>
    0.55
    íncia
    0.55
    risse
    0.54
    TextBoxColumn
    0.54
    Activations Density 0.504%

    No Known Activations