© 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. 206140
    Prev
    Next
    INDEX
    Explanations

    too often

    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
    ↵
    1.14
    (
    0.99
    ต์
    0.98
    ین
    0.87
    ด
    0.86
    開始
    0.83
    व
    0.80
    กับ
    0.79
    ти
    0.79
    ên
    0.78
    POSITIVE LOGITS
    ;
    1.05
    ؛
    1.02
    1.01
    ){
    0.98
    ))
    0.95
    ،
    0.95
    :
    0.94
    )).
    0.93
    ه
    0.93
     insulting
    0.92
    Activations Density 0.002%

    No Known Activations