© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37008
    Prev
    Next
    INDEX
    Explanations

    howdy, train, R.O.C., howdy ho

    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
    ing
    0.71
     расска
    0.59
    ס
    0.57
     for
    0.55
     expliqué
    0.55
     össz
    0.54
    ნიშვნელ
    0.54
     ERISA
    0.54
    ة
    0.54
     quedaría
    0.54
    POSITIVE LOGITS
     is
    0.84
     does
    0.75
     processed
    0.72
    de
    0.70
    ‌ای
    0.70
    َ
    0.68
    나
    0.63
    t
    0.62
    ’
    0.61
    다
    0.61
    Activations Density 0.031%

    No Known Activations