© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45480
    Prev
    Next
    INDEX
    Explanations

    full employment, retirement age, fullscreen api

    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_3_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
    Ак
    0.61
    Кли
    0.60
    ível
    0.59
    Анд
    0.59
    s
    0.59
    Це
    0.58
     linseed
    0.57
    Роз
    0.57
    潙
    0.57
    Бы
    0.57
    POSITIVE LOGITS
    ת
    0.89
    ли
    0.85
    ם
    0.82
    েন
    0.75
    ম
    0.72
    ту
    0.71
    ur
    0.70
    د
    0.69
    ২
    0.69
    TY
    0.68
    Activations Density 0.006%

    No Known Activations