© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5508
    Prev
    Next
    INDEX
    Explanations

    function comments

    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_3_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
    তে
    2.31
    卷积
    2.04
    ry
    2.03
    ктери
    2.01
    ০
    1.99
    伎
    1.95
    𝐭
    1.92
     $|\
    1.91
    𝐩
    1.90
    𝐡
    1.87
    POSITIVE LOGITS
    ি
    2.11
    ت
    2.08
    ясь
    2.06
    ів
    1.98
    즌
    1.93
    i
    1.92
     reputed
    1.72
    ी
    1.71
     tandem
    1.71
     концу
    1.70
    Activations Density 0.001%

    No Known Activations