© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9330
    Prev
    Next
    INDEX
    Explanations

    break this down

    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_13_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
    y
    0.33
    view
    0.31
    li
    0.31
    man
    0.31
    g
    0.31
    world
    0.30
    id
    0.30
    yang
    0.30
    p
    0.30
    iny
    0.30
    POSITIVE LOGITS
     характеристи
    0.34
     tailles
    0.31
     adaptés
    0.30
     Ejemplo
    0.29
     বৈশিষ্ট
    0.29
     относятся
    0.28
     животных
    0.27
     disassemble
    0.27
     Exemple
    0.26
     Сколько
    0.26
    Activations Density 0.453%

    No Known Activations