© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61822
    Prev
    Next
    INDEX
    Explanations

    immediate

    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_11_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
    。
    0.60
    л
    0.60
     mul
    0.57
     सत्ता
    0.55
    मेरे
    0.55
    ִי
    0.54
     mehreren
    0.52
     gă
    0.52
     மீது
    0.51
     принад
    0.51
    POSITIVE LOGITS
    v
    0.59
    jections
    0.57
     Ν
    0.54
    w
    0.53
    č
    0.53
    ča
    0.52
    ك
    0.52
    %";
    0.52
    IT
    0.51
     Χ
    0.50
    Activations Density 0.000%

    No Known Activations