© 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. 246575
    Prev
    Next
    INDEX
    Explanations

    docker-compose configuration

    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
    jwa
    0.41
    吸收
    0.41
     tar
    0.39
     tk
    0.38
     penicillin
    0.38
     ABSORBED
    0.38
    キ
    0.38
     TFS
    0.38
    dien
    0.37
     absorbed
    0.37
    POSITIVE LOGITS
    loader
    0.42
    𝑛
    0.41
    porter
    0.40
    منابع
    0.39
    uristic
    0.39
    درسة
    0.39
     দশমিক
    0.39
    دور
    0.38
     Reload
    0.37
    reload
    0.37
    Activations Density 0.000%

    No Known Activations