© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207186
    Prev
    Next
    INDEX
    Explanations

    ‘

    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_20_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
     sebagai
    0.55
     Freed
    0.50
     команд
    0.49
    ghed
    0.49
     ರಲ್ಲಿ
    0.48
     besondere
    0.47
    И
    0.47
     зокрема
    0.47
    م
    0.46
     Sebagai
    0.46
    POSITIVE LOGITS
     rectangles
    0.48
     acest
    0.42
    ན
    0.42
    toni
    0.41
     yellows
    0.41
    enei
    0.41
     impatience
    0.41
    This
    0.39
     arrogance
    0.39
    ந்தைய
    0.39
    Activations Density 0.000%

    No Known Activations