© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12437
    Prev
    Next
    INDEX
    Explanations

    words that stand out as unusual or unexpected

    oai_token-act-pair · gemini-2.0-flash

    say "out"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للمعارف
    -0.65
    HttpFoundation
    -0.59
    RenderAtEndOf
    -0.59
    endpush
    -0.58
    Hentet
    -0.57
     AttributeSet
    -0.54
    ieteur
    -0.54
    RUnlock
    -0.54
    Bioaccumulative
    -0.54
    simpleType
    -0.54
    POSITIVE LOGITS
     out
    3.08
    out
    2.91
    Out
    2.52
     Out
    2.47
    OUT
    2.25
     OUT
    2.22
    outs
    2.16
     outs
    1.83
    アウト
    1.63
     Outs
    1.38
    Activations Density 3.448%

    No Known Activations