© 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. 13197
    Prev
    Next
    INDEX
    Explanations

    text referring to a quantity or degree, especially those that are "high" or "low"

    oai_token-act-pair · gemini-2.0-flash

    High/low values

    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
     متعلقه
    -0.57
     viennent
    -0.51
     مشين
    -0.49
    AlterField
    -0.49
    addEdge
    -0.49
     termica
    -0.48
     sää
    -0.48
    حوالہ
    -0.48
     الرياضيه
    -0.47
    Зноскі
    -0.47
    POSITIVE LOGITS
     amount
    0.74
     fufficient
    0.71
    WebElementEntity
    0.68
     geringe
    0.66
    ligible
    0.65
     low
    0.65
     myſelf
    0.64
     enough
    0.64
     decreased
    0.63
     propOrder
    0.62
    Activations Density 1.963%

    No Known Activations