© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59757
    Prev
    Next
    INDEX
    Explanations

    как [question word]

    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_2_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
    一
    0.99
    \
    0.86
    N
    0.85
     you
    0.82
     an
    0.82
    ı
    0.80
     one
    0.79
    \">
    0.77
    -
    0.77
     pły
    0.73
    POSITIVE LOGITS
    اب
    1.09
    ات
    1.00
    in
    0.84
    تي
    0.81
    s
    0.80
    ts
    0.79
    ्स
    0.79
    с
    0.79
    स
    0.78
    ран
    0.75
    Activations Density 0.000%

    No Known Activations