© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228503
    Prev
    Next
    INDEX
    Explanations

    risks to

    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_6_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
    스
    0.82
     Па
    0.78
    Ве
    0.77
    ﻪ
    0.76
    ]}\
    0.75
    ﺸ
    0.75
    has
    0.74
     וא
    0.73
     முழுவதும்
    0.73
     (
    0.72
    POSITIVE LOGITS
    ਰ
    0.75
    ur
    0.71
    ну
    0.68
     airflow
    0.66
     in
    0.66
     chops
    0.65
     речь
    0.65
    o
    0.65
    om
    0.63
     cushions
    0.63
    Activations Density 0.001%

    No Known Activations