© 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. 34342
    Prev
    Next
    INDEX
    Explanations

    Operators

    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
    Cycling
    0.35
     सेल्सियस
    0.34
    ╕
    0.33
    abilia
    0.33
    േയ
    0.32
    ocytosis
    0.32
    涝
    0.32
     cycling
    0.32
    掬
    0.31
    atório
    0.31
    POSITIVE LOGITS
     Convent
    0.40
     contributors
    0.39
     Contributors
    0.37
     Bars
    0.35
     Wren
    0.35
     Auxiliary
    0.35
     lekar
    0.35
     adverb
    0.35
     Hir
    0.34
     laman
    0.34
    Activations Density 0.002%

    No Known Activations