© 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. 24320
    Prev
    Next
    INDEX
    Explanations

    z.B

    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
     effic
    0.75
     assertFalse
    0.73
    '
    0.70
    0.67
     форма
    0.65
     ilustraciones
    0.65
     автомо
    0.63
     clearContext
    0.63
     statistiques
    0.62
     hetzelfde
    0.62
    POSITIVE LOGITS
    es
    1.08
    i
    0.96
    el
    0.93
    z
    0.89
    os
    0.89
    am
    0.86
    ampe
    0.82
    h
    0.82
    ES
    0.79
    esi
    0.78
    Activations Density 0.001%

    No Known Activations