© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206265
    Prev
    Next
    INDEX
    Explanations

    Wikipedia links

    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_25_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
    뻐
    0.27
    ೆಯನ್ನು
    0.26
     waging
    0.25
    갔
    0.25
     malignant
    0.24
     transmission
    0.24
    λη
    0.24
     prosecuted
    0.23
     Buddh
    0.23
     homosexual
    0.23
    POSITIVE LOGITS
    ┇
    0.29
    International
    0.27
     الَّ
    0.27
     وزار
    0.26
     इंटरनेशनल
    0.26
     neun
    0.26
    rior
    0.26
    ье
    0.26
     hö
    0.25
     único
    0.25
    Activations Density 0.001%

    No Known Activations