© 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. 37138
    Prev
    Next
    INDEX
    Explanations

    waste time or energy

    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
    х
    0.67
    ।
    0.67
    의
    0.66
    ،
    0.65
     speck
    0.64
     présent
    0.60
    iin
    0.60
    iť
    0.60
     disposit
    0.60
    ल
    0.60
    POSITIVE LOGITS
    𝚎
    0.63
    College
    0.62
    ۸
    0.60
     College
    0.59
    ۷
    0.58
    ╅
    0.57
    DFS
    0.56
    ↵
    0.56
    难度
    0.56
    য়ার
    0.54
    Activations Density 0.002%

    No Known Activations