© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26074
    Prev
    Next
    INDEX
    Explanations

    5 or V following certain words

    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_10_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
    s
    1.34
    스
    1.29
    ne
    1.27
    n
    1.25
    li
    1.19
    ন
    1.09
    ن
    1.06
    d
    1.02
    ل
    1.02
    ž
    1.01
    POSITIVE LOGITS
    ’
    0.95
     consape
    0.85
     have
    0.82
     similares
    0.81
     кілько
    0.80
    ہ
    0.80
    -
    0.80
     peruse
    0.77
     quinto
    0.76
     inadmissible
    0.75
    Activations Density 0.080%

    No Known Activations