© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41771
    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_22_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
     тест
    0.49
     ನಿಜ
    0.45
     вважа
    0.45
     правой
    0.44
    ‴
    0.44
    ıc
    0.44
    اتر
    0.43
    więks
    0.43
     каж
    0.42
     холо
    0.42
    POSITIVE LOGITS
    Oracle
    0.44
    И
    0.42
    (
    0.42
    _
    0.42
     مسلح
    0.40
     out
    0.40
    Yield
    0.39
    Ла
    0.39
    out
    0.38
    ति
    0.38
    Activations Density 0.000%

    No Known Activations