© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245543
    Prev
    Next
    INDEX
    Explanations

    stop working

    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_40_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
    entering
    0.41
     تنها
    0.39
     entering
    0.38
    سلم
    0.38
    嚼
    0.37
     climbing
    0.37
    }}^{*}
    0.37
     sipping
    0.36
     quedarse
    0.36
     заниматься
    0.36
    POSITIVE LOGITS
    ře
    0.40
    ,&
    0.40
    erves
    0.38
     Ordinary
    0.37
    Rated
    0.36
     flash
    0.36
    ”;
    0.36
    Flutter
    0.36
    Meet
    0.36
    ്രാ
    0.36
    Activations Density 0.002%

    No Known Activations