© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206041
    Prev
    Next
    INDEX
    Explanations

    don't hesitate to ask questions

    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
    Repeat
    0.46
     repeating
    0.44
     ܐ
    0.44
     répét
    0.44
    重复
    0.43
     repetitions
    0.43
     repeatedly
    0.41
     rép
    0.41
     repet
    0.41
    repet
    0.41
    POSITIVE LOGITS
    undance
    0.43
    irteen
    0.42
    <unused63>
    0.40
     расши
    0.40
     স্র
    0.38
     считается
    0.35
     dianggap
    0.35
     flex
    0.35
     Seen
    0.35
    uctive
    0.34
    Activations Density 0.003%

    No Known Activations