© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51842
    Prev
    Next
    INDEX
    Explanations

    every

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    Pretty
    0.45
    day
    0.43
    Cold
    0.42
    thing
    0.40
    நடிக
    0.40
    ƾ
    0.40
    ୍ୟ
    0.39
    permutation
    0.39
     ٹک
    0.37
     Electromagnetic
    0.37
    POSITIVE LOGITS
     several
    0.57
     vài
    0.54
     few
    0.53
     Several
    0.53
     몇
    0.52
     couple
    0.50
     Few
    0.48
     nekoliko
    0.47
     несколько
    0.46
    Several
    0.46
    Activations Density 0.003%

    No Known Activations