© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26691
    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_40_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
    坭
    0.43
    钤
    0.39
    ட்டால்
    0.38
    ቲ
    0.38
    marginal
    0.37
    คอน
    0.36
    쌓
    0.36
    !"));
    0.36
    affiliation
    0.36
    gium
    0.35
    POSITIVE LOGITS
     Lact
    0.40
     Mess
    0.40
     Hard
    0.40
     הנ
    0.40
     hard
    0.39
     HARD
    0.39
    žev
    0.37
    妿
    0.37
     Rest
    0.36
     perched
    0.36
    Activations Density 0.097%

    No Known Activations