© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130186
    Prev
    Next
    INDEX
    Explanations

    Swiss followed by descriptors

    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_1_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
    ي
    1.64
    '
    1.49
    i
    1.47
    y
    1.34
    ו
    1.31
    o
    1.30
    e
    1.29
    k
    1.29
    י
    1.27
    ে
    1.16
    POSITIVE LOGITS
    ка
    1.23
    на
    1.16
    いる
    0.97
     և
    0.95
    ne
    0.94
     п
    0.88
    ре
    0.88
    lijke
    0.87
    нару
    0.86
    िने
    0.86
    Activations Density 0.001%

    No Known Activations