© 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. 78950
    Prev
    Next
    INDEX
    Explanations

    sources citationscdc

    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
     chhoti
    0.31
     एबी
    0.30
    :"
    0.30
    ದ್ದ
    0.30
    粥
    0.29
    ="//
    0.29
    orting
    0.29
    tbLabel
    0.29
     `"
    0.29
     divulg
    0.28
    POSITIVE LOGITS
    ുകൾ
    0.29
     keel
    0.29
     deliver
    0.29
    roughs
    0.29
    ృ
    0.29
    Server
    0.28
     což
    0.28
    дела
    0.28
     ရက်
    0.28
    ্কার
    0.28
    Activations Density 0.005%

    No Known Activations