© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3472
    Prev
    Next
    INDEX
    Explanations

    units with exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ো
    1.74
    ս
    1.73
    व
    1.64
    де
    1.63
     flurry
    1.60
    el
    1.59
    श
    1.56
     иң
    1.55
    us
    1.55
     wanders
    1.53
    POSITIVE LOGITS
    }|
    1.95
    }-
    1.85
    Aye
    1.83
     σύμφωνα
    1.74
    $%
    1.72
    s
    1.66
    ┣
    1.64
    鬚
    1.64
     Дей
    1.61
    дко
    1.61
    Activations Density 0.004%

    No Known Activations