© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33226
    Prev
    Next
    INDEX
    Explanations

    job location

    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
    Negative Logits
    a
    0.73
    e
    0.73
    in
    0.70
    bs
    0.66
    Ꮽ
    0.64
     incisions
    0.62
     adept
    0.61
    be
    0.61
    ko
    0.59
    coefficients
    0.59
    POSITIVE LOGITS
    ل
    0.77
    و
    0.70
    lə
    0.64
    ι
    0.63
    ست
    0.61
    ו
    0.61
    ويه
    0.60
    వ
    0.60
    ه‌ی
    0.59
    รอ
    0.59
    Activations Density 0.003%

    No Known Activations