© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33067
    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_40_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
    
    0.37
     stirring
    0.36
     provoking
    0.35
    äub
    0.34
    TrackAngle
    0.34
     triggers
    0.34
     coles
    0.34
    オーダー
    0.33
    ೋದ
    0.33
    ¶
    0.33
    POSITIVE LOGITS
     azione
    0.46
    アクション
    0.45
     действия
    0.43
     action
    0.41
     actions
    0.41
     acción
    0.41
     azioni
    0.41
     akci
    0.40
     ACTION
    0.40
     Aktion
    0.39
    Activations Density 0.000%

    No Known Activations