© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79112
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ни
    1.70
    و
    1.45
    सँग
    1.41
    نا
    1.32
    ל
    1.26
    後
    1.25
    خدام
    1.23
    as
    1.22
    пусти
    1.16
    но
    1.15
    POSITIVE LOGITS
     הראש
    1.38
    clientes
    1.30
    t
    1.30
     работа
    1.28
     öğrenc
    1.27
     plasmids
    1.25
    IL
    1.20
     हालात
    1.20
     އަ
    1.19
     السعود
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.