© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220786
    Prev
    Next
    INDEX
    Explanations

    JSON structure keys and values

    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_31_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
     صار
    0.32
    猩
    0.31
     BSc
    0.31
    ョ
    0.31
    ="|
    0.29
     الحكوم
    0.28
     Bangkok
    0.28
    回来了
    0.28
     cellulose
    0.28
    手法
    0.28
    POSITIVE LOGITS
     વિશ્વ
    0.33
    }`);
    0.32
     അല്ലെങ്കിൽ
    0.31
     regardless
    0.31
     malgré
    0.31
     trotz
    0.30
    眨
    0.30
     அருள்
    0.30
    pé
    0.30
     irrespective
    0.29
    Activations Density 0.005%

    No Known Activations