© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3292
    Prev
    Next
    INDEX
    Explanations

    socket options

    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
    s
    0.82
    ে
    0.80
    ات
    0.67
    ের
    0.67
    ы
    0.66
    また
    0.62
    形式
    0.62
    ח
    0.61
    な
    0.60
    {\
    0.58
    POSITIVE LOGITS
    née
    0.81
    ﺩ
    0.76
    avamo
    0.74
     itulah
    0.74
    naph
    0.73
    𝓷
    0.73
    ্রো
    0.72
     gdy
    0.72
     LHS
    0.71
    遑
    0.70
    Activations Density 0.001%

    No Known Activations