© 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. 3718
    Prev
    Next
    INDEX
    Explanations

    Zerodium, hub, nude, keys

    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
    ાર
    2.10
     insuring
    1.87
    Terminate
    1.85
     Объ
    1.75
    वेळी
    1.71
    தற்காக
    1.70
    ן
    1.70
    ीन
    1.69
    个月
    1.69
    boBox
    1.69
    POSITIVE LOGITS
    问题
    1.76
    الم
    1.65
    देव
    1.60
    bold
    1.59
    การ
    1.56
    新型
    1.56
    లో
    1.53
    彡
    1.53
    人員
    1.51
     współprac
    1.49
    Activations Density 0.000%

    No Known Activations