© 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. 131416
    Prev
    Next
    INDEX
    Explanations

    listing or citation ending

    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
    é
    1.00
    et
    0.95
    ႉ
    0.83
     измене
    0.82
     оказалось
    0.82
    usic
    0.80
     dotycz
    0.80
     Pierws
    0.79
     иностран
    0.77
     причинам
    0.77
    POSITIVE LOGITS
    ב
    1.29
    ם
    1.06
    s
    1.00
     is
    0.99
     to
    0.98
    は
    0.95
    ض
    0.90
    أ
    0.88
    ς
    0.87
     an
    0.87
    Activations Density 0.027%

    No Known Activations