© 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. 230808
    Prev
    Next
    INDEX
    Explanations

    Baixa district

    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
    u
    1.11
    ;
    0.98
    ,
    0.95
    ä
    0.93
    ien
    0.93
    ine
    0.84
    ?
    0.82
    z
    0.80
     to
    0.80
    le
    0.75
    POSITIVE LOGITS
    0.73
    K
    0.65
    ята
    0.64
    IS
    0.62
    必須
    0.61
    Golem
    0.61
     我們
    0.60
    Wasser
    0.60
    時間
    0.59
    Vater
    0.59
    Activations Density 0.000%

    No Known Activations