© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91976
    Prev
    Next
    INDEX
    Explanations

    pushing the boundaries

    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_11_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
    لاک
    0.64
    作曲
    0.63
     宮
    0.63
    除非
    0.61
    h
    0.61
    ⤠
    0.61
    रेक्ट
    0.60
    اوار
    0.59
    اديه
    0.58
    ج
    0.58
    POSITIVE LOGITS
     –
    0.68
    a
    0.68
    in
    0.61
     onslaught
    0.60
     !!
    0.56
    als
    0.56
    alist
    0.55
     годи
    0.55
    ers
    0.55
     perspectives
    0.54
    Activations Density 0.006%

    No Known Activations