© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110059
    Prev
    Next
    INDEX
    Explanations

    phenomena

    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_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
    1.71
    า
    1.69
    y
    1.68
    on
    1.42
    w
    1.34
    া
    1.34
    u
    1.29
    ir
    1.17
    oq
    1.17
    un
    1.16
    POSITIVE LOGITS
    ,
    0.99
    는데
    0.95
     hintergrund
    0.91
     freighter
    0.88
     cemented
    0.88
    la
    0.83
     celebrity
    0.82
     Tige
    0.81
     interplanetary
    0.81
     whiteboard
    0.80
    Activations Density 0.001%

    No Known Activations