© 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. 18679
    Prev
    Next
    INDEX
    Explanations

    choose the one

    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
     wherein
    0.38
    ებით
    0.37
     সফলতা
    0.37
    .],
    0.37
    ၌
    0.36
     সংখ্যক
    0.35
    .])
    0.35
    :],
    0.35
     where
    0.34
     где
    0.34
    POSITIVE LOGITS
     celui
    0.42
     των
    0.42
     той
    0.41
     тот
    0.41
    도의
    0.39
    iai
    0.38
    dah
    0.38
     quickest
    0.37
     Synth
    0.37
     그
    0.37
    Activations Density 0.256%

    No Known Activations