© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89234
    Prev
    Next
    INDEX
    Explanations

    order doesn't matter

    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_23_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
    freeze
    0.36
    pita
    0.33
    $-
    0.33
    集合
    0.33
    utage
    0.33
    了他的
    0.33
    和一个
    0.32
    局
    0.32
     Investigations
    0.32
     Cyclic
    0.32
    POSITIVE LOGITS
     outra
    0.46
     எங்களுக்கு
    0.44
     çalış
    0.41
     vogliamo
    0.41
     acrescent
    0.40
     প্রচারণা
    0.40
     ajuda
    0.40
     लेके
    0.39
     sampai
    0.39
     ayuda
    0.39
    Activations Density 0.002%

    No Known Activations