© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209671
    Prev
    Next
    INDEX
    Explanations

    company brands and products

    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
    رځ
    0.48
    Lapangan
    0.46
    Scrim
    0.46
    डेजा
    0.46
    Kennedy
    0.43
    ᱑
    0.42
    ︽
    0.42
    ោធ
    0.41
    lere
    0.40
     katth
    0.40
    POSITIVE LOGITS
     Coastal
    0.48
     coastal
    0.46
    Coastal
    0.45
     тех
    0.41
     जिनमें
    0.41
     upset
    0.40
     ответственность
    0.40
    直径
    0.39
     relay
    0.39
     Watershed
    0.39
    Activations Density 0.001%

    No Known Activations