© 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. 147276
    Prev
    Next
    INDEX
    Explanations

    app

    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
    app
    0.88
     app
    0.80
    App
    0.70
    ऐप
    0.66
     App
    0.63
     앱
    0.63
    APP
    0.62
    アプリ
    0.61
    앱
    0.58
    les
    0.56
    POSITIVE LOGITS
    letti
    0.52
    leting
    0.49
    LETE
    0.48
    ятся
    0.47
    ícias
    0.47
     Retail
    0.47
    mselves
    0.46
     retail
    0.45
    lets
    0.44
    ing
    0.44
    Activations Density 0.002%

    No Known Activations