© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193666
    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_4_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
     iha
    0.49
    .
    0.48
    香
    0.45
    5
    0.45
    但
    0.44
     bike
    0.43
    May
    0.43
    lais
    0.41
     tags
    0.41
    TB
    0.41
    POSITIVE LOGITS
     béton
    0.64
    <unused617>
    0.59
     воспринима
    0.58
     Δια
    0.57
    
    0.57
    !</
    0.57
    êle
    0.55
    タイプ
    0.54
    キャ
    0.53
     ಸಂಖ್ಯ
    0.53
    Activations Density 0.000%

    No Known Activations