© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181453
    Prev
    Next
    INDEX
    Explanations

    css button properties

    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
    着
    0.33
    制
    0.30
    clamp
    0.29
     مک
    0.29
     meestal
    0.28
     প্রান্ত
    0.28
     الصحة
    0.28
    磷
    0.28
    selector
    0.28
    alkeeper
    0.28
    POSITIVE LOGITS
    Thriller
    0.33
     intrigue
    0.31
     contrived
    0.31
     .”
    0.31
    ჯგუფი
    0.31
     curiosity
    0.31
    विर
    0.30
     Fudge
    0.30
     freelance
    0.29
    Ltd
    0.29
    Activations Density 0.001%

    No Known Activations