© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140416
    Prev
    Next
    INDEX
    Explanations

    competitive programming problems

    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_12_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
     conquer
    0.52
     acoust
    0.52
    -
    0.49
     chocolat
    0.49
     caché
    0.47
     contagion
    0.46
     hike
    0.46
     etter
    0.46
     মুজিবর
    0.46
     hiding
    0.46
    POSITIVE LOGITS
    ão
    0.51
    łu
    0.51
    lą
    0.50
     Haryana
    0.49
     Saying
    0.49
    夷
    0.47
     पद्ध
    0.47
    ön
    0.46
    ä
    0.45
    ļu
    0.45
    Activations Density 0.003%

    No Known Activations