Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 33-GEMMASCOPE-2-TRANSCODER-262K
    4. 261731
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_33_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.83
     för
    0.71
     vä
    0.71
     vam
    0.70
     "=",
    0.69
     maxLength
    0.69
     kath
    0.68
     "-",
    0.66
    最大
    0.66
     cf
    0.65
    POSITIVE LOGITS
    ello
    0.95
    esses
    0.93
    axes
    0.91
     Nursing
    0.90
    ዝና
    0.90
    ires
    0.89
    uos
    0.88
    Wiring
    0.88
     Wiring
    0.87
    ayos
    0.87
    Activations Density 0.000%

    No Known Activations