© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143249
    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_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    僭
    0.48
     Etappe
    0.48
     Trailer
    0.47
     repres
    0.46
    nCurrent
    0.46
     تبدی
    0.45
     मच्छर
    0.45
    舢
    0.45
    StatusCode
    0.45
     Transportation
    0.44
    POSITIVE LOGITS
    З
    0.56
    ，
    0.52
    chi
    0.45
    ஜெ
    0.44
    க
    0.44
    comfort
    0.44
    gg
    0.43
    За
    0.43
    連
    0.42
    WIL
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.