© 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. 3449
    Prev
    Next
    INDEX
    Explanations

    re- prefixes

    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
    べき
    1.04
    rukh
    0.97
     Zusatz
    0.87
     Plow
    0.85
     않을
    0.82
    સ
    0.82
    امت
    0.81
     রাখতে
    0.80
    UAGE
    0.80
     adecuada
    0.79
    POSITIVE LOGITS
     vigor
    1.03
    ร์
    0.95
    ع
    0.94
    ط
    0.94
     एकदा
    0.90
     vigour
    0.89
     Bored
    0.87
    $("
    0.87
    Juven
    0.85
    ீடு
    0.81
    Activations Density 0.120%

    No Known Activations