© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107966
    Prev
    Next
    INDEX
    Explanations

    ю followed by punctuation or "дро"

    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_1_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
    '
    1.52
     is
    1.41
     was
    1.15
    on
    1.14
    ij
    1.13
     has
    1.09
    ai
    1.04
     Recursos
    0.99
    ig
    0.96
     by
    0.94
    POSITIVE LOGITS
    с
    1.30
    л
    1.24
    н
    1.20
    لای
    1.01
    newline
    1.00
    न
    1.00
    resize
    0.97
    زی
    0.92
    reverse
    0.92
    し
    0.91
    Activations Density 0.000%

    No Known Activations