© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239260
    Prev
    Next
    INDEX
    Explanations

    hsv_to_rgb, read_json, connectedComponents, unified_diff, pivot_table, temperature, solvePnP, encode

    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_25_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
     \
    0.30
    vious
    0.29
    Х
    0.29
    },
    0.28
    Â
    0.28
    ̣
    0.28
     համ
    0.27
    â
    0.27
    ca
    0.26
    をはじめ
    0.26
    POSITIVE LOGITS
     doGet
    0.35
    绎
    0.34
     తగ్
    0.33
    রিষ্ঠ
    0.33
     lancio
    0.33
    жкой
    0.33
     conspiracy
    0.32
    ٹ
    0.32
     assertEquals
    0.32
     Crush
    0.31
    Activations Density 0.002%

    No Known Activations