© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209099
    Prev
    Next
    INDEX
    Explanations

    2D grid or array representations

    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_20_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
     करण्याचा
    0.24
    ίνουν
    0.22
    门户
    0.22
    﨑
    0.21
    选项
    0.21
     questioned
    0.21
     делаю
    0.21
    widehat
    0.21
    阖
    0.20
     paved
    0.20
    POSITIVE LOGITS
    uric
    0.21
     ink
    0.20
    olines
    0.20
    стями
    0.20
     inks
    0.20
    etel
    0.19
    ancies
    0.19
    uth
    0.19
    ورس
    0.19
    éries
    0.19
    Activations Density 0.004%

    No Known Activations