© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11237
    Prev
    Next
    INDEX
    Explanations

    words related to accountability, delegation, and progression

    oai_token-act-pair · gemini-2.0-flash

    responsibility and initiative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.23
     arché
    -0.66
     pédagogique
    -0.64
     législation
    -0.58
     asiatique
    -0.57
     oike
    -0.57
     fieltro
    -0.57
    HideFlags
    -0.57
     történ
    -0.57
     tournage
    -0.56
    POSITIVE LOGITS
    thâu
    0.77
    elter
    0.75
    DoubleQuotes
    0.74
    вік
    0.72
    urement
    0.68
     <",
    0.66
    逅
    0.64
    setVerticalGroup
    0.63
    leski
    0.63
    auré
    0.62
    Activations Density 0.808%

    No Known Activations