© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249756
    Prev
    Next
    INDEX
    Explanations

    say loop

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     passada
    0.39
     passou
    0.37
     полном
    0.37
     Desenvolvimento
    0.36
     passa
    0.36
    มอบ
    0.35
     ты
    0.35
    쩐
    0.35
     перший
    0.34
     भरना
    0.34
    POSITIVE LOGITS
     an
    0.54
    Internal
    0.46
    Intern
    0.45
    Query
    0.43
    FO
    0.43
    with
    0.43
    WAL
    0.42
    we
    0.42
    部分
    0.41
    wings
    0.41
    Activations Density 0.002%

    No Known Activations