© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46815
    Prev
    Next
    INDEX
    Explanations

    importing Python libraries

    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_10_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
     B
    0.57
    air
    0.52
     R
    0.48
     C
    0.48
     N
    0.47
    t
    0.46
    ha
    0.44
     H
    0.44
     A
    0.44
     .
    0.43
    POSITIVE LOGITS
    \
    0.59
     비롯
    0.46
     livres
    0.45
    おります
    0.44
    \%,
    0.41
     by
    0.39
    IdleSync
    0.38
     уви
    0.38
    로
    0.38
     прогно
    0.37
    Activations Density 0.003%

    No Known Activations