© 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. 132318
    Prev
    Next
    INDEX
    Explanations

    involve

    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
     in
    1.07
    ри
    0.90
     další
    0.88
    ất
    0.84
    ur
    0.83
    rix
    0.82
     δεύτε
    0.82
    ى
    0.82
    į
    0.80
     في
    0.80
    POSITIVE LOGITS
    t
    1.50
    s
    1.50
     to
    1.22
    m
    1.17
    ের
    1.15
    mc
    1.02
    u
    1.02
     incendi
    1.02
    tb
    0.94
    ج
    0.93
    Activations Density 0.000%

    No Known Activations