© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9890
    Prev
    Next
    INDEX
    Explanations

    references to card games and dictionaries

    oai_token-act-pair · gemini-2.0-flash

    technical terms and phrases

    np_token-act-pair-logits · gpt-4o-mini

    blog/definition card

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     instrument
    -0.48
     Instrument
    -0.44
     instruments
    -0.44
    нак
    -0.43
    pecu
    -0.43
     custom
    -0.43
    brero
    -0.41
    AppData
    -0.41
    URLException
    -0.41
     Custom
    -0.41
    POSITIVE LOGITS
    Демографія
    0.67
    parsedMessage
    0.66
     vPvB
    0.61
    "=>"
    0.60
    TypedDataSet
    0.60
    évaluateur
    0.59
    expandindo
    0.56
    GridColumn
    0.56
    Попис
    0.56
    WebServlet
    0.56
    Activations Density 0.973%

    No Known Activations