© 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. 13075
    Prev
    Next
    INDEX
    Explanations

    questions asking for help or suggestions.

    oai_token-act-pair · gemini-2.0-flash

    requests for help

    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
    ym
    -0.49
    nvarchar
    -0.48
    complexContent
    -0.48
    長
    -0.47
    godic
    -0.46
     ده
    -0.46
    ?
    -0.45
    립
    -0.42
    LayoutStyle
    -0.42
     mor
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.79
     purpoſe
    0.76
     pleaſure
    0.74
     greateſt
    0.73
     feroit
    0.70
     itſelf
    0.70
    RenderAtEndOf
    0.70
     kasarigan
    0.69
    ^(@)
    0.68
    tonode
    0.68
    Activations Density 17.060%

    No Known Activations