© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45603
    Prev
    Next
    INDEX
    Explanations

    what you have in mind

    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_3_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
    as
    0.96
    al
    0.93
     as
    0.92
    1
    0.92
    os
    0.84
    0
    0.84
    ed
    0.78
    ie
    0.77
    ai
    0.75
    at
    0.73
    POSITIVE LOGITS
    ע
    0.76
    示す
    0.67
     Ке
    0.66
     Тем
    0.66
     Чтобы
    0.65
     Ро
    0.65
     Чем
    0.65
     Национа
    0.64
     Dmitry
    0.64
     Tổ
    0.64
    Activations Density 0.001%

    No Known Activations