© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58907
    Prev
    Next
    INDEX
    Explanations

    informational titles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    <bos>
    0.41
    诸
    0.39
    ّ
    0.38
     cuando
    0.38
     remarkably
    0.38
    0.38
     zuerst
    0.37
     بزر
    0.37
     før
    0.37
    ם
    0.37
    POSITIVE LOGITS
     TestAvg
    0.52
     സൃ
    0.47
     Linden
    0.46
    zmdi
    0.45
     Hölder
    0.45
     !,
    0.44
    ambra
    0.43
     Ashram
    0.43
     Aditya
    0.42
    icating
    0.42
    Activations Density 0.000%

    No Known Activations