© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 253035
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ,
    0.96
     ,"
    0.85
     )
    0.77
     ).
    0.77
     ,'
    0.74
     ),
    0.73
     ."
    0.73
     ,\
    0.71
     )}
    0.69
     ”
    0.68
    POSITIVE LOGITS
    :-)
    0.42
    antages
    0.37
     прось
    0.36
    necessarily
    0.36
    ్‌
    0.35
    (${
    0.35
    숑
    0.34
    ண்டும்
    0.34
     cheats
    0.34
     revistas
    0.33
    Activations Density 0.000%

    No Known Activations