© 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. 124274
    Prev
    Next
    INDEX
    Explanations

    p5js programs

    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
    ﺭ
    0.75
     branca
    0.65
    Bit
    0.63
    UM
    0.61
    Favorite
    0.61
    Book
    0.61
    wd
    0.61
    లె
    0.61
    Donate
    0.61
    hr
    0.60
    POSITIVE LOGITS
    د
    0.91
    a
    0.82
    نی
    0.76
    ه
    0.71
    ing
    0.70
    ется
    0.69
    ties
    0.67
    гідно
    0.67
    ة
    0.66
    다
    0.66
    Activations Density 0.000%

    No Known Activations