© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37800
    Prev
    Next
    INDEX
    Explanations

    maroon frescos

    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_3_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
     to
    0.73
    렜
    0.67
     considerate
    0.64
    ۰
    0.63
     stric
    0.62
    ோ
    0.62
    stücke
    0.59
    ﮐ
    0.59
     الطيب
    0.58
     Badal
    0.58
    POSITIVE LOGITS
    ని
    0.73
    ı
    0.67
    我
    0.67
    ث
    0.66
    тре
    0.65
    โดย
    0.65
    นี้
    0.65
    朹
    0.65
    C
    0.64
    他
    0.63
    Activations Density 0.000%

    No Known Activations