© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14845
    Prev
    Next
    INDEX
    Explanations

    code snippets and the word "multi"

    oai_token-act-pair · gemini-2.0-flash

    multi

    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
    keits
    -0.73
    ה
    -0.68
     
    -0.63
    gance
    -0.61
    HEL
    -0.60
    nitive
    -0.59
    urence
    -0.59
    lemented
    -0.59
     nb
    -0.59
    tiges
    -0.59
    POSITIVE LOGITS
    脚注の使い方
    1.14
     enfans
    1.13
     lèvres
    1.02
     religieuses
    1.02
     genoux
    0.97
     larmes
    0.94
     religieux
    0.93
     jambes
    0.93
     ouverts
    0.91
     épaules
    0.91
    Activations Density 1.312%

    No Known Activations