© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203738
    Prev
    Next
    INDEX
    Explanations

    pecan

    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_6_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
    도
    0.98
     ແລະ
    0.95
     xương
    0.92
     μια
    0.90
     در
    0.89
     milieux
    0.88
    ม
    0.88
     및
    0.85
     locaux
    0.85
     علاقے
    0.85
    POSITIVE LOGITS
    ”
    1.34
    ى
    1.08
     that
    1.03
    "
    1.01
    í
    0.99
    }'
    0.98
    ',
    0.96
    ْم
    0.95
    в
    0.94
    }(
    0.93
    Activations Density 0.001%

    No Known Activations