© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42219
    Prev
    Next
    INDEX
    Explanations

    need help with tasks

    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_3_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
    1.05
    K
    1.03
    К
    1.02
    N
    1.00
    C
    0.95
    B
    0.91
    M
    0.87
    Q
    0.87
    J
    0.86
    V
    0.85
    POSITIVE LOGITS
    </strong>
    0.80
    рт
    0.79
    йн
    0.75
    лом
    0.72
    าย
    0.70
    仕上げ
    0.69
    0
    0.68
     terapi
    0.68
    拢
    0.64
    ക്കുറിച്ച്
    0.64
    Activations Density 0.001%

    No Known Activations