© 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. 38481
    Prev
    Next
    INDEX
    Explanations

    Devanagari script

    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
    h
    1.38
    t
    0.99
    v
    0.93
    y
    0.92
    m
    0.88
    b
    0.80
    p
    0.80
    c
    0.79
    i
    0.76
    n
    0.73
    POSITIVE LOGITS
    ка
    0.99
    кать
    0.96
    ۰۰
    0.86
    니다
    0.86
    ले
    0.82
    కి
    0.81
    ங்கள்
    0.81
    스가
    0.81
    ப்பொரு
    0.78
    アカウント
    0.77
    Activations Density 0.002%

    No Known Activations