© 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. 45886
    Prev
    Next
    INDEX
    Explanations

    lay this out

    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
    ئت
    0.50
    ôm
    0.45
    äischen
    0.45
    贸
    0.45
    <0x8F>
    0.44
    ина
    0.44
    язку
    0.44
    adev
    0.43
    жая
    0.43
    ạch
    0.43
    POSITIVE LOGITS
    n
    0.55
     i
    0.51
     MARC
    0.49
     Gallows
    0.49
     sam
    0.46
     IG
    0.46
     Gunnar
    0.46
     Cris
    0.46
     MOST
    0.46
     Sharpe
    0.46
    Activations Density 0.000%

    No Known Activations