© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1655
    Prev
    Next
    INDEX
    Explanations

    graph diagram syntax

    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_40_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
    ייתה
    0.42
     오른쪽
    0.39
    paintbrush
    0.38
    ulagway
    0.37
    ⑨
    0.37
     حمل
    0.36
    unting
    0.36
     الإمارات
    0.36
    iae
    0.36
    versible
    0.36
    POSITIVE LOGITS
     TimeSpan
    0.48
     सन
    0.41
     hourglass
    0.39
     bathing
    0.38
     iteration
    0.37
     Mushroom
    0.37
     Tiempo
    0.36
    ﺝ
    0.36
     standardised
    0.36
     кү
    0.35
    Activations Density 0.003%

    No Known Activations