© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205711
    Prev
    Next
    INDEX
    Explanations

    climate change

    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_20_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
    荒
    0.36
     jurnal
    0.34
     новых
    0.34
    otro
    0.33
    ޫ
    0.33
    筏
    0.33
     Фран
    0.32
     Europeo
    0.32
    gerald
    0.32
    franz
    0.32
    POSITIVE LOGITS
    、
    0.33
    Dimensions
    0.32
    亠
    0.30
     secretions
    0.30
    тус
    0.30
    ٘
    0.30
     dég
    0.30
     vinegar
    0.30
    혐
    0.29
     preclude
    0.29
    Activations Density 0.002%

    No Known Activations