© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122614
    Prev
    Next
    INDEX
    Explanations

    software: download, version, update

    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_37_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
     lay
    0.39
     muff
    0.39
    pst
    0.39
     laying
    0.38
     loss
    0.38
     lays
    0.37
     p
    0.37
     guest
    0.37
     kust
    0.37
    परा
    0.36
    POSITIVE LOGITS
    DU
    0.43
    エイ
    0.41
    Version
    0.40
     ανα
    0.39
    Versions
    0.39
     প্রসার
    0.38
    Fitz
    0.37
    ଡ
    0.37
    acido
    0.37
     Versions
    0.37
    Activations Density 0.000%

    No Known Activations