© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30559
    Prev
    Next
    INDEX
    Explanations

    new daily, new york, new masters

    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_31_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
    筛选
    0.42
    fiz
    0.40
     veins
    0.38
     taint
    0.36
    锁
    0.36
     biomarkers
    0.36
    \{-\
    0.36
     munc
    0.36
     nix
    0.36
     getMenuInflater
    0.35
    POSITIVE LOGITS
    чі
    0.39
     Rud
    0.38
    inputType
    0.38
    Restart
    0.37
    Nev
    0.37
    prototype
    0.36
     Prototype
    0.36
    Rud
    0.36
    ἤ
    0.36
    scholar
    0.35
    Activations Density 0.001%

    No Known Activations