© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9293
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Gericht
    0.70
     vár
    0.68
     широкий
    0.67
     نړۍ
    0.67
     Moc
    0.66
     Độ
    0.66
    getKey
    0.65
    舆
    0.64
    ั่น
    0.64
    主管部门
    0.64
    POSITIVE LOGITS
     follow
    0.73
    follow
    0.72
     followup
    0.70
    Loops
    0.67
     follows
    0.67
    Follow
    0.66
     vuel
    0.63
     Follow
    0.63
     FOLLOW
    0.63
     LOOP
    0.62
    Activations Density 0.001%

    No Known Activations