© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    body language and physical state

    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
    ية
    0.96
    Unlike
    0.95
     inroads
    0.92
    ুলে
    0.91
    రించ
    0.91
     Vgl
    0.90
    ³
    0.90
     acclaim
    0.89
    ミス
    0.88
     эт
    0.86
    POSITIVE LOGITS
     SafeArea
    1.33
     thể
    1.10
     entero
    1.04
    ng
    0.96
     schematically
    0.94
     floated
    0.94
    𝔸
    0.94
     spoiled
    0.93
     совокуп
    0.93
    ရပ်
    0.92
    Activations Density 0.091%

    No Known Activations