© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124678
    Prev
    Next
    INDEX
    Explanations

    slipknot

    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_37_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
    鳎
    0.40
    <unused24>
    0.39
    тын
    0.39
     تلیفون
    0.39
    ']).
    0.38
    甭
    0.38
     স্বীকৃতির
    0.38
     पढ़ा
    0.37
    夗
    0.37
     écriv
    0.37
    POSITIVE LOGITS
     satin
    0.39
     bath
    0.39
     silently
    0.39
     satur
    0.38
     capturing
    0.38
     smells
    0.37
    Mar
    0.37
     inex
    0.37
     infused
    0.37
    Lore
    0.37
    Activations Density 0.000%

    No Known Activations