© 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. 42768
    Prev
    Next
    INDEX
    Explanations

    legal and academic citation

    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
     ín
    0.55
     наме
    0.51
    อร์
    0.50
    ían
    0.50
     complete
    0.50
    ing
    0.49
    岕
    0.49
     "
    0.48
     cuad
    0.48
     real
    0.48
    POSITIVE LOGITS
    ρι
    0.57
    avourable
    0.56
    citep
    0.55
    METHODS
    0.55
    佛教
    0.54
    доступ
    0.54
     بخاری
    0.54
    示例
    0.53
    苙
    0.53
     Согласно
    0.53
    Activations Density 0.016%

    No Known Activations