© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4876
    Prev
    Next
    INDEX
    Explanations

    font-family values

    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_39_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
     Typing
    0.43
     ছো
    0.42
     Staaten
    0.41
     TYPE
    0.40
     സോഷ്യ
    0.40
    社交
    0.37
    ecimiento
    0.37
    綣
    0.37
     Type
    0.37
     typename
    0.37
    POSITIVE LOGITS
     family
    0.53
     families
    0.50
    family
    0.47
     родствен
    0.43
    families
    0.41
     Family
    0.41
     семей
    0.41
     가족
    0.40
     परिजन
    0.39
     família
    0.39
    Activations Density 0.017%

    No Known Activations