© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130193
    Prev
    Next
    INDEX
    Explanations

    stay

    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_50_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
    শন
    0.39
     मच्छ
    0.37
    elleen
    0.36
    GIS
    0.36
    ຣ
    0.35
    рика
    0.34
    ▲
    0.34
    రు
    0.34
    শনের
    0.33
    дика
    0.33
    POSITIVE LOGITS
     ghost
    0.48
    ghost
    0.45
     জীবিত
    0.42
     nema
    0.42
    hej
    0.41
    弇
    0.40
    Ghost
    0.40
    bj
    0.39
     powod
    0.39
     valet
    0.39
    Activations Density 0.001%

    No Known Activations