© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38918
    Prev
    Next
    INDEX
    Explanations

    materials and dimensions

    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_11_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
    2
    0.50
    filter
    0.47
     candles
    0.46
    incare
    0.45
     contributing
    0.44
    dor
    0.43
    filters
    0.42
     filters
    0.42
    Rendering
    0.42
    a
    0.41
    POSITIVE LOGITS
     élu
    0.52
     elekt
    0.52
     Polynesia
    0.52
     gás
    0.51
    виси
    0.49
     vasena
    0.49
     vutta
    0.48
    㐱
    0.48
     vutto
    0.47
     denounced
    0.46
    Activations Density 0.060%

    No Known Activations