© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    references to the human body, possession, and death

    oai_token-act-pair · 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
     their
    -0.49
     autorytatywna
    -0.48
     ihres
    -0.47
    peg
    -0.46
    monių
    -0.45
     its
    -0.45
    runApp
    -0.43
    例文帳に追加
    -0.43
    fé
    -0.40
     nennt
    -0.40
    POSITIVE LOGITS
    WebElementEntity
    0.75
    uxxxx
    0.72
    IContainer
    0.71
     ModelExpression
    0.69
    MENAFN
    0.66
     ſtate
    0.63
     purpoſe
    0.62
     TextAppearance
    0.60
    jstor
    0.60
     ſche
    0.59
    Activations Density 0.751%

    No Known Activations