© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83843
    Prev
    Next
    INDEX
    Explanations

    pencil skirts

    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_0_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
    t
    2.27
    '
    2.03
    dır
    1.98
    to
    1.96
    de
    1.75
    -
    1.73
    iii
    1.71
    i
    1.71
    that
    1.70
    м
    1.67
    POSITIVE LOGITS
     faisait
    1.31
    お店
    1.27
    كبر
    1.24
     dovoljno
    1.24
     όχι
    1.20
     يس
    1.15
     fique
    1.15
    お子
    1.14
     كان
    1.13
     ficou
    1.13
    Activations Density 0.000%

    No Known Activations