© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49635
    Prev
    Next
    INDEX
    Explanations

    dw, byte, length, Wharf, b"

    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_10_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
    t
    0.52
    細かい
    0.51
    on
    0.47
     Carter
    0.47
     Bugünkü
    0.46
     substituir
    0.46
    汚
    0.46
     chanel
    0.45
     relevante
    0.44
     bahwa
    0.44
    POSITIVE LOGITS
     بي
    0.46
    和服务
    0.46
    雙
    0.44
     أح
    0.44
     ترى
    0.44
    츰
    0.44
     ثانوي
    0.44
     BIM
    0.43
    么
    0.43
    ContentTypes
    0.43
    Activations Density 0.000%

    No Known Activations