© 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. 25633
    Prev
    Next
    INDEX
    Explanations

    four legs or walking on all fours

    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
    have
    1.06
    o
    0.85
    in
    0.77
    a
    0.77
    D
    0.74
    -
    0.73
    reverse
    0.71
    [
    0.69
    Have
    0.68
    P
    0.68
    POSITIVE LOGITS
     animaux
    0.85
     animais
    0.85
     ortak
    0.84
     arthrop
    0.83
     oiseaux
    0.80
     animals
    0.80
     rabies
    0.80
     vertebrates
    0.79
    ທ່ານ
    0.78
     mammals
    0.77
    Activations Density 0.025%

    No Known Activations