© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3486
    Prev
    Next
    INDEX
    Explanations

    arguments that include historical references to slavery

    oai_token-act-pair · gemini-2.0-flash

    names of historical leaders

    np_token-act-pair-logits · gpt-4o-mini

    Famous leaders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    XmlAccessType
    -0.66
     fronte
    -0.49
     Moya
    -0.47
     laude
    -0.47
    lanie
    -0.46
     Lett
    -0.46
    jelent
    -0.45
    WSGI
    -0.45
     рее
    -0.44
     indag
    -0.44
    POSITIVE LOGITS
     Roosevelt
    0.85
     Hitler
    0.84
     FDR
    0.83
     Lincoln
    0.83
     Eisenhower
    0.82
    FDR
    0.78
     Gorbachev
    0.77
     Cæsar
    0.73
     Churchill
    0.73
     Napoleon
    0.73
    Activations Density 4.882%

    No Known Activations