© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15236
    Prev
    Next
    INDEX
    Explanations

    cache, lock, sql, fetch, raw

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     appendage
    0.33
     enqueue
    0.32
     wardrobe
    0.31
     encryption
    0.31
     કર્યા
    0.31
     appendages
    0.30
    <unused2135>
    0.30
     পরী
    0.29
    莳
    0.29
     ге
    0.29
    POSITIVE LOGITS
    states
    0.34
     STATES
    0.32
    स्व
    0.30
    σο
    0.30
    λι
    0.30
    so
    0.29
     Because
    0.29
    no
    0.29
    gi
    0.29
     Çünkü
    0.29
    Activations Density 0.024%

    No Known Activations