© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45168
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions like tan and beta

    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_13_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
     vouchers
    0.60
    繃
    0.60
    రకు
    0.60
     bă
    0.54
     methotrexate
    0.54
     sheets
    0.52
     taut
    0.52
     proliferative
    0.51
     prothorax
    0.50
    мії
    0.50
    POSITIVE LOGITS
    Portada
    0.65
    nombre
    0.61
    main
    0.59
    ↵↵
    0.59
    java
    0.55
    ↵↵↵
    0.55
    ↵↵↵↵
    0.55
    Imagen
    0.54
    gorod
    0.54
    original
    0.53
    Activations Density 0.000%

    No Known Activations