© 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. 151482
    Prev
    Next
    INDEX
    Explanations

    conditions and production

    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
    이
    2.16
    й
    2.06
    йся
    1.41
    йга
    1.11
    が
    1.07
    йки
    1.05
    йын
    1.01
    йон
    0.85
    Й
    0.84
    йл
    0.83
    POSITIVE LOGITS
    ந
    0.38
    TryParse
    0.35
     impuls
    0.33
    撃
    0.33
    OutputFile
    0.33
     catap
    0.33
    Yesterday
    0.32
    rightbar
    0.32
     ж
    0.32
    Ni
    0.32
    Activations Density 0.003%

    No Known Activations