© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82970
    Prev
    Next
    INDEX
    Explanations

    surprisingly complex or difficult

    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_29_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
    ք
    0.36
     Regel
    0.35
    Catalog
    0.33
    樍
    0.33
    quot
    0.33
     vuttam
    0.33
    arctic
    0.32
    ék
    0.32
     충분
    0.32
    mml
    0.32
    POSITIVE LOGITS
     shocking
    0.51
     shockingly
    0.49
    竟然
    0.48
    居然
    0.48
    失败
    0.46
     चौंका
    0.46
     inexplic
    0.45
     surprisingly
    0.45
    愕
    0.44
     shock
    0.43
    Activations Density 0.036%

    No Known Activations