© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92106
    Prev
    Next
    INDEX
    Explanations

    say "uppercase letter"

    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_60_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
    a
    0.50
    available
    0.48
    i
    0.44
    is
    0.42
    formulas
    0.42
    the
    0.41
    aesthetic
    0.39
    consider
    0.39
    resources
    0.39
    answers
    0.39
    POSITIVE LOGITS
     F
    0.73
     K
    0.64
     G
    0.63
     W
    0.61
     M
    0.56
     R
    0.56
     S
    0.55
     H
    0.54
     J
    0.53
     D
    0.52
    Activations Density 0.008%

    No Known Activations