© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80935
    Prev
    Next
    INDEX
    Explanations

    rating or score scale

    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_29_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
    野球
    0.39
    འི་
    0.37
     PATH
    0.36
     Paradigm
    0.35
    ИС
    0.35
    ന്ഥ
    0.35
    胭
    0.35
    じて
    0.33
     شهید
    0.33
     TRUST
    0.33
    POSITIVE LOGITS
    。《
    0.38
     тобто
    0.35
     exemption
    0.33
    ebilirsiniz
    0.32
     உண்ட
    0.31
     ہوگا۔
    0.31
     हाम
    0.30
     escaped
    0.30
    бла
    0.29
     pró
    0.29
    Activations Density 0.009%

    No Known Activations