© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260941
    Prev
    Next
    INDEX
    Explanations

    VP followed by parentheses or "hunt"

    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_10_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
    })_{
    0.76
    FLOAT
    0.73
    +|
    0.72
     njegova
    0.71
     njegov
    0.70
     ै
    0.69
    <unused558>
    0.67
     ඒවා
    0.67
    <unused1761>
    0.67
     Sobolev
    0.65
    POSITIVE LOGITS
     mó
    0.76
     należy
    0.71
     باید
    0.66
     cling
    0.66
    жение
    0.65
    ablemente
    0.64
     необходимо
    0.64
    зм
    0.64
    ின்
    0.64
    ebilir
    0.63
    Activations Density 0.000%

    No Known Activations