© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63893
    Prev
    Next
    INDEX
    Explanations

    imports and module declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    
    0.41
    Valent
    0.36
     πραγμα
    0.36
     rzeczyw
    0.36
     Ambro
    0.36
    FocusValue
    0.35
    нє
    0.35
    精
    0.35
     প্রে
    0.35
     മലയാള
    0.35
    POSITIVE LOGITS
     Obrador
    0.43
    bootstrap
    0.41
    شرات
    0.41
    Gast
    0.40
    घ्र
    0.40
    !<
    0.40
     exporter
    0.38
     boc
    0.38
     Gast
    0.38
    Labels
    0.37
    Activations Density 0.000%

    No Known Activations