© 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. 50421
    Prev
    Next
    INDEX
    Explanations

    javascript method calls

    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
    ֙
    0.35
    髙
    0.34
    бні
    0.33
    的研究
    0.32
     condens
    0.32
    שט
    0.32
    meyi
    0.31
    які
    0.31
    ᚖ
    0.31
     INSPIRE
    0.31
    POSITIVE LOGITS
     Lining
    0.34
    不仅仅
    0.33
     worrying
    0.33
     passi
    0.33
    Anything
    0.32
     additional
    0.32
     preventable
    0.31
     Anything
    0.31
     tambahan
    0.31
     linha
    0.31
    Activations Density 0.002%

    No Known Activations