© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203247
    Prev
    Next
    INDEX
    Explanations

    examples and specific cases

    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_25_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
    jectories
    0.37
     scoreboard
    0.35
     scorecard
    0.33
    𝚞
    0.32
     groove
    0.32
     metamorph
    0.32
     transformation
    0.32
     boardwalk
    0.32
     Rewrite
    0.31
    ధాన
    0.31
    POSITIVE LOGITS
    ITT
    0.37
    ྱི་
    0.37
     Posteriormente
    0.36
     대학
    0.35
    ével
    0.35
    ्यावर
    0.34
     mencionar
    0.34
    ~)
    0.34
     ncol
    0.33
     एलिमेंट्स
    0.33
    Activations Density 0.006%

    No Known Activations