© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242013
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     Ат
    0.48
     Bhi
    0.44
     Luft
    0.42
    があれば
    0.42
     Air
    0.41
     ihr
    0.40
     Erfahr
    0.39
     Thế
    0.38
    謳
    0.38
     อีก
    0.38
    POSITIVE LOGITS
    ry
    0.45
    ngo
    0.42
    shirts
    0.42
    ng
    0.40
    ness
    0.40
    shirt
    0.40
    decade
    0.40
    amending
    0.40
    ests
    0.39
    dir
    0.39
    Activations Density 0.000%

    No Known Activations