© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13266
    Prev
    Next
    INDEX
    Explanations

    pain points

    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
    Ｘ
    0.36
    axi
    0.33
    ｐ
    0.33
    рия
    0.33
    ۰
    0.33
    𝘫
    0.33
     khám
    0.33
    ’
    0.33
    st
    0.32
    in
    0.32
    POSITIVE LOGITS
     dificultades
    0.45
     tribulations
    0.45
     الكهرب
    0.43
     difficulties
    0.41
    lieder
    0.38
     проблеми
    0.38
     concat
    0.38
     reloj
    0.37
     difficultés
    0.37
     تغيير
    0.36
    Activations Density 0.025%

    No Known Activations