© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 543
    Prev
    Next
    INDEX
    Explanations

    python versions

    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_40_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
    rad
    0.40
    Slack
    0.39
     Slack
    0.39
     lo
    0.39
     Gar
    0.39
     Way
    0.38
     CD
    0.38
     W
    0.37
     cot
    0.37
     Weg
    0.37
    POSITIVE LOGITS
    apanam
    0.38
     mediaPlayer
    0.37
    海上
    0.37
    okhlov
    0.36
     politič
    0.36
    ज़र
    0.36
    твра
    0.36
    athin
    0.36
     एमसीक्यू
    0.35
     ورځې
    0.35
    Activations Density 0.012%

    No Known Activations