© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9267
    Prev
    Next
    INDEX
    Explanations

    medical journals

    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_13_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
    ة
    0.42
    HEX
    0.39
    ᱖
    0.38
    jud
    0.37
    SHE
    0.36
    B
    0.36
    F
    0.35
    メ
    0.35
    잦
    0.35
    ಿಸ್
    0.35
    POSITIVE LOGITS
     Issue
    0.36
     severed
    0.36
     pd
    0.35
     beginnings
    0.33
     don
    0.33
     available
    0.32
     begin
    0.32
     pawn
    0.32
     offending
    0.31
     Appl
    0.31
    Activations Density 0.003%

    No Known Activations