© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131765
    Prev
    Next
    INDEX
    Explanations

    a medida que

    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_6_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
    -
    0.87
    يا
    0.85
    и
    0.84
    '
    0.79
    ы
    0.79
    其他
    0.76
    िस
    0.75
    ב
    0.74
    ма
    0.73
    ৮
    0.72
    POSITIVE LOGITS
    2
    0.93
    1
    0.89
    0
    0.76
    di
    0.75
    in
    0.73
    g
    0.73
     H
    0.72
     Sath
    0.72
    den
    0.72
     Katy
    0.71
    Activations Density 0.000%

    No Known Activations