© 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. 85563
    Prev
    Next
    INDEX
    Explanations

    science, technology, physics engines

    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
    ה
    1.02
    ע
    0.95
    ка
    0.89
    a
    0.84
    ن
    0.83
    er
    0.80
    ↵↵
    0.77
     as
    0.77
    ه
    0.75
    ти
    0.73
    POSITIVE LOGITS
    ট
    0.76
    0.66
    ।,
    0.63
     Queue
    0.63
     kwiat
    0.63
    Jetzt
    0.62
     Namen
    0.62
    Ș
    0.62
     janvier
    0.61
     Zambia
    0.61
    Activations Density 0.006%

    No Known Activations