© 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. 57877
    Prev
    Next
    INDEX
    Explanations

    /

    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
     What
    0.70
     IS
    0.57
    !
    0.56
     Just
    0.54
    ?
    0.53
     Why
    0.52
     WHAT
    0.52
     JUST
    0.49
    ;
    0.48
     One
    0.47
    POSITIVE LOGITS
    a
    0.76
    when
    0.53
    were
    0.53
    go
    0.45
    ten
    0.44
    o
    0.44
    was
    0.43
    Ten
    0.43
    whenever
    0.43
    is
    0.42
    Activations Density 0.004%

    No Known Activations