© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83915
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
    Negative Logits
     skyscrapers
    0.45
     suicide
    0.43
     churches
    0.43
     pretty
    0.42
     GNP
    0.41
     "
    0.41
     countries
    0.41
     Portland
    0.41
     sniper
    0.41
     treatment
    0.40
    POSITIVE LOGITS
     মস
    0.42
     яких
    0.42
    getahuan
    0.41
     associativity
    0.41
    ಾರು
    0.40
    funciones
    0.40
    Cooper
    0.40
    Structural
    0.39
    POSITORY
    0.39
    岸
    0.39
    Activations Density 0.000%

    No Known Activations