© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124350
    Prev
    Next
    INDEX
    Explanations

    code closing brackets, comments, or function definitions

    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_37_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
     isOn
    0.41
    (['
    0.39
    aków
    0.38
    INS
    0.38
     tắc
    0.38
     !==
    0.37
    isOn
    0.37
     ^^
    0.36
    lef
    0.36
     पूछ
    0.36
    POSITIVE LOGITS
    ?");
    0.42
    гами
    0.40
    ?";
    0.40
    ?",
    0.38
    Func
    0.37
     trim
    0.36
     Connection
    0.36
    ?')
    0.36
    ӵ
    0.36
     connection
    0.36
    Activations Density 0.000%

    No Known Activations