© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63271
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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_59_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
    寰
    0.40
    Fel
    0.38
    гато
    0.36
     মি
    0.36
    த்தா
    0.36
    インタビュー
    0.36
     छैन
    0.35
    Թ
    0.35
    et
    0.35
     Crescent
    0.35
    POSITIVE LOGITS
     उप
    0.39
     Зна
    0.37
     त्र
    0.36
    ккей
    0.36
    quette
    0.35
    ,|
    0.35
     ని
    0.35
     향
    0.34
     mal
    0.34
    arXiv
    0.34
    Activations Density 0.001%

    No Known Activations