© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 200024
    Prev
    Next
    INDEX
    Explanations

    multilingual text endings

    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_9_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
    constants
    0.55
    index
    0.55
    a
    0.53
    import
    0.52
    resources
    0.52
    from
    0.51
    buildings
    0.51
    equipment
    0.50
    birds
    0.50
    fueled
    0.50
    POSITIVE LOGITS
    唾
    0.48
     Spiele
    0.44
     seguinte
    0.43
    িয়াল
    0.43
     günstig
    0.43
    ალ
    0.42
     espiritual
    0.41
    ။
    0.41
     Vorsch
    0.41
    如下
    0.40
    Activations Density 0.000%

    No Known Activations