© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248526
    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_56_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
     prih
    0.45
    ῆ
    0.44
    ָ
    0.44
    inputId
    0.43
    🇭
    0.38
    omass
    0.38
     Extensions
    0.37
     sharpening
    0.36
    ))}{
    0.35
     sari
    0.34
    POSITIVE LOGITS
     gonz
    0.42
     rychle
    0.36
     écologique
    0.34
     rav
    0.34
    ინისტრ
    0.34
     թվ
    0.34
     बल्लेबाजी
    0.34
    ത്യ
    0.33
     hool
    0.33
     civiles
    0.33
    Activations Density 0.000%

    No Known Activations