© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20338
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    和其他
    0.37
     istnie
    0.36
    㳑
    0.35
    beiten
    0.35
     পুঁ
    0.34
    albeit
    0.32
    orgetown
    0.32
     esistono
    0.32
     pior
    0.31
    尌
    0.31
    POSITIVE LOGITS
    ＆
    0.59
    และ
    0.59
     અને
    0.58
     और
    0.56
     ও
    0.55
     និង
    0.55
     आणि
    0.54
     एवं
    0.52
     ಮತ್ತು
    0.52
     ಹಾಗೂ
    0.51
    Activations Density 0.595%

    No Known Activations