© 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. 8542
    Prev
    Next
    INDEX
    Explanations

    anonymous functions and callbacks

    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
     मछली
    0.44
     बुनिया
    0.40
    ,'"
    0.39
    𝗯
    0.38
    𝑻
    0.38
     scie
    0.38
     SPSS
    0.37
     Serviço
    0.37
    ,]$
    0.36
    CollectedField
    0.35
    POSITIVE LOGITS
    (
    0.41
    nit
    0.38
    dro
    0.36
    nj
    0.35
     Holz
    0.34
    nth
    0.34
     by
    0.33
     regolare
    0.33
     Glover
    0.33
    nr
    0.32
    Activations Density 0.134%

    No Known Activations