© 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. 34033
    Prev
    Next
    INDEX
    Explanations

    vigilante

    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
    1.15
    ه
    0.80
    d
    0.73
    eby
    0.70
    ა
    0.70
    لي
    0.68
    一种
    0.66
    i
    0.66
    dat
    0.64
    1
    0.64
    POSITIVE LOGITS
    ר
    0.86
    ૦
    0.83
    ы
    0.79
    ς
    0.76
    τη
    0.75
    ط
    0.73
    つ
    0.70
    ০০
    0.70
    ओं
    0.69
    ۰۰
    0.68
    Activations Density 0.000%

    No Known Activations