© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199185
    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_12_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
    수가
    0.54
    暾
    0.51
    t
    0.51
    서트
    0.50
    洹
    0.49
     ngừa
    0.48
    수로
    0.48
     oligodend
    0.47
     saffron
    0.46
    งาน
    0.46
    POSITIVE LOGITS
     Chief
    0.48
     Doch
    0.48
     inicio
    0.46
    ↵
    0.45
    ↵↵
    0.41
    od
    0.41
     militaire
    0.41
    ↵↵↵
    0.41
     Trump
    0.41
     Military
    0.41
    Activations Density 0.000%

    No Known Activations