© 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. 133895
    Prev
    Next
    INDEX
    Explanations

    email authentication DKIM signing

    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
    на
    1.11
    ك
    1.08
    ки
    0.91
     كه
    0.89
    <0x80>
    0.88
    bindingFields
    0.87
    此同时
    0.84
    اق
    0.81
    اين
    0.81
     ו
    0.79
    POSITIVE LOGITS
    ।
    1.16
    ä
    1.04
    Y
    1.02
    िंग
    1.01
    л
    1.01
    in
    0.98
    L
    0.96
    ô
    0.94
    ेड
    0.93
    ।)
    0.93
    Activations Density 0.000%

    No Known Activations