© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25358
    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_10_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
    akn
    0.47
    ydı
    0.44
     daughter
    0.43
     ‘
    0.43
     Courts
    0.42
     gold
    0.41
     CER
    0.41
     Arithmetic
    0.41
     peacetime
    0.41
     arithmetic
    0.40
    POSITIVE LOGITS
    ي
    0.62
     יותר
    0.53
     добав
    0.53
     síntomas
    0.53
     baixo
    0.52
     nasional
    0.51
    ם
    0.51
    ک
    0.51
     stehen
    0.50
    シンプル
    0.50
    Activations Density 0.000%

    No Known Activations