© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139093
    Prev
    Next
    INDEX
    Explanations

    diff command usage

    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_37_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
     menjadi
    0.37
     niñas
    0.37
     funcionalidades
    0.36
    煖
    0.35
    inke
    0.35
     Compd
    0.35
     fonctions
    0.35
    νοντας
    0.34
     ಪುಟ
    0.34
     modos
    0.34
    POSITIVE LOGITS
     سەر
    0.44
    Фа
    0.39
    近
    0.38
    อร์
    0.38
     Ridd
    0.37
    चि
    0.36
     Placeholder
    0.36
     task
    0.35
     Metric
    0.35
     gev
    0.35
    Activations Density 0.002%

    No Known Activations