© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13937
    Prev
    Next
    INDEX
    Explanations

    sentence description or story

    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
    福
    0.36
     read
    0.35
    гії
    0.35
     readers
    0.35
     regrets
    0.35
     minimize
    0.34
     යන
    0.34
    idency
    0.34
     രണ്ട
    0.34
    读
    0.33
    POSITIVE LOGITS
     Bhajan
    0.36
    acet
    0.31
     Capp
    0.30
    Limite
    0.30
    Cap
    0.30
     कैप
    0.30
    Tracks
    0.30
    stuk
    0.30
    ometro
    0.30
     Profess
    0.29
    Activations Density 0.016%

    No Known Activations