© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110725
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
     a
    1.48
    ,
    1.10
    ?
    1.09
    ,"
    1.00
    ;
    0.99
    \
    0.98
    ä
    0.96
    á
    0.95
    ,【
    0.93
    ,’
    0.90
    POSITIVE LOGITS
    for
    1.04
     for
    1.03
    و
    1.01
    h
    1.00
    p
    0.99
    ર
    0.96
    น
    0.92
     болезнь
    0.88
    रो
    0.87
     durée
    0.85
    Activations Density 0.000%

    No Known Activations