© 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. 11572
    Prev
    Next
    INDEX
    Explanations

    binary search or bisect

    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
    ố
    0.37
    DAN
    0.37
    letic
    0.35
    Rafael
    0.35
    Sticky
    0.35
    ovac
    0.34
    ávání
    0.34
    Iz
    0.34
     Stuck
    0.34
    //////
    0.34
    POSITIVE LOGITS
     bis
    2.09
     Bis
    1.85
    Bis
    1.73
    bis
    1.63
     binary
    1.50
     BIS
    1.38
     Binary
    1.37
    binary
    1.29
    BIS
    1.28
    Binary
    1.23
    Activations Density 0.099%

    No Known Activations