© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32947
    Prev
    Next
    INDEX
    Explanations

    daily service

    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_31_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
     호텔
    0.44
     kaj
    0.40
     кварта
    0.40
     conférence
    0.39
    пози
    0.39
     пози
    0.39
    ⅓
    0.39
     quartos
    0.37
     positiv
    0.37
    㺫
    0.37
    POSITIVE LOGITS
    Daily
    0.65
     daily
    0.64
    daily
    0.60
     Daily
    0.57
     codzien
    0.57
     ежедневно
    0.56
    每天
    0.55
     DAILY
    0.53
     ежеднев
    0.52
     quotidienne
    0.51
    Activations Density 0.001%

    No Known Activations