© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169833
    Prev
    Next
    INDEX
    Explanations

    tiramisu

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ड्रा
    0.46
     dec
    0.40
     Pap
    0.36
    যন্ত্র
    0.36
    extension
    0.36
    ប់
    0.36
    നേ
    0.35
    譏
    0.35
     Spain
    0.35
     RPA
    0.35
    POSITIVE LOGITS
    zys
    0.40
     замі
    0.39
     Massimo
    0.38
     አማ
    0.38
    yth
    0.37
     squiggle
    0.37
     assicur
    0.37
    otika
    0.36
    挥
    0.36
     신
    0.36
    Activations Density 0.000%

    No Known Activations