© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79018
    Prev
    Next
    INDEX
    Explanations

    quick judgment, wit, wins, thinking, action

    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
     rivet
    0.31
    竞
    0.31
    ม่
    0.30
    ポップ
    0.30
     adecuadas
    0.30
     основу
    0.30
    pop
    0.30
    越し
    0.30
    娄
    0.30
    硞
    0.29
    POSITIVE LOGITS
     IgG
    0.34
    beautiful
    0.30
     zatim
    0.30
    Century
    0.30
     EGFR
    0.30
    opatra
    0.29
     সালমান
    0.29
     uprav
    0.29
    oflav
    0.29
    ourt
    0.29
    Activations Density 0.009%

    No Known Activations