© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52162
    Prev
    Next
    INDEX
    Explanations

    public method or function definition

    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_31_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
     कानूनों
    0.38
    炵
    0.38
    ляр
    0.37
    教堂
    0.37
    nonzero
    0.36
    缙
    0.36
    colare
    0.35
     thereunder
    0.35
    筞
    0.35
    Crim
    0.34
    POSITIVE LOGITS
     TU
    0.47
     functional
    0.46
     Functional
    0.45
     static
    0.40
     promoting
    0.40
     synt
    0.40
     Function
    0.39
    ပြု
    0.39
     analyzing
    0.38
    functional
    0.38
    Activations Density 0.001%

    No Known Activations