© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37936
    Prev
    Next
    INDEX
    Explanations

    rush hour

    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_3_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
    та
    0.70
    젝트
    0.66
     (
    0.59
    ти
    0.57
    A
    0.55
    ాల
    0.54
    开发者
    0.52
     schwierig
    0.51
    ం
    0.51
    те
    0.50
    POSITIVE LOGITS
    h
    0.75
     Rush
    0.60
     ağı
    0.59
     پاک
    0.57
     کار
    0.57
     ولی
    0.57
     реки
    0.56
    field
    0.55
     rush
    0.55
     oblik
    0.55
    Activations Density 0.000%

    No Known Activations