© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133781
    Prev
    Next
    INDEX
    Explanations

    waterfront locations and features

    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
    ↵↵
    1.47
    us
    1.04
    ,
    1.02
    3
    0.97
    k
    0.96
     of
    0.95
    7
    0.90
    (
    0.87
    kek
    0.86
    ro
    0.85
    POSITIVE LOGITS
    ری
    1.40
    ре
    1.15
    на
    1.14
    и
    1.04
    ру
    1.03
    ма
    0.95
    работка
    0.95
     وړاندوینه
    0.93
    お金
    0.93
    ،
    0.93
    Activations Density 0.000%

    No Known Activations