© 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. 17072
    Prev
    Next
    INDEX
    Explanations

    import React

    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
    リース
    0.38
     tap
    0.37
    ()<<
    0.37
    سات
    0.36
     innocence
    0.36
     irrevers
    0.35
     ancient
    0.35
    Tabuleiro
    0.35
     rank
    0.35
    >();
    0.35
    POSITIVE LOGITS
    濵
    0.40
    HAM
    0.39
    HER
    0.39
     latitudine
    0.39
     benutzt
    0.38
    KM
    0.38
    addie
    0.38
    炉
    0.38
     मील
    0.37
    र्भ
    0.37
    Activations Density 0.001%

    No Known Activations