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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35714
    Prev
    Next
    INDEX
    Explanations

    stick, knot, jack, top, shot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    قي
    0.72
    чи
    0.66
    ૬
    0.65
    fifths
    0.64
    دي
    0.63
    ográf
    0.63
    تقديم
    0.63
     ۵
    0.63
    在哪
    0.63
    ド
    0.62
    POSITIVE LOGITS
     of
    0.96
    ter
    0.86
     for
    0.83
     the
    0.73
    ters
    0.65
    两
    0.64
    kan
    0.64
    sad
    0.64
    OMe
    0.63
    negara
    0.62
    Activations Density 0.016%

    No Known Activations