© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198450
    Prev
    Next
    INDEX
    Explanations

    log.fatal

    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_15_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
    CHES
    0.59
     対象
    0.54
     महंगा
    0.54
    壌
    0.54
    CHI
    0.53
    गल
    0.52
    าค
    0.52
    燙
    0.52
    ール
    0.52
    CHANT
    0.52
    POSITIVE LOGITS
    med
    0.49
     Hermann
    0.48
    ched
    0.48
     ाट
    0.46
    ued
    0.45
     sollte
    0.45
    рованная
    0.45
    ividade
    0.45
     неза
    0.44
     könnte
    0.44
    Activations Density 0.001%

    No Known Activations