© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195639
    Prev
    Next
    INDEX
    Explanations

    operations system entities

    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_26_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
    Location
    0.33
    éristiques
    0.33
    ጥነት
    0.33
    彈
    0.33
    app
    0.32
    Scanner
    0.32
    Strategy
    0.32
    Perm
    0.32
     '');
    0.32
    Skull
    0.32
    POSITIVE LOGITS
     qualche
    0.38
    ҝ
    0.38
     kai
    0.38
     sogen
    0.37
     Colomb
    0.37
     jednu
    0.37
    蘖
    0.37
     Kla
    0.36
     chien
    0.35
     kie
    0.35
    Activations Density 0.007%

    No Known Activations