© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91132
    Prev
    Next
    INDEX
    Explanations

    Satan, Russian words,guru, odes

    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
    a
    0.98
    h
    0.87
    itab
    0.86
    r
    0.83
    s
    0.80
    el
    0.76
    em
    0.76
    ali
    0.76
    ed
    0.75
    RICAL
    0.73
    POSITIVE LOGITS
    ל
    0.84
    ן
    0.83
    يس
    0.82
    性
    0.80
    ير
    0.79
    ست
    0.68
    سم
    0.67
    larını
    0.67
     ليست
    0.66
    ك
    0.66
    Activations Density 0.000%

    No Known Activations