© 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. 11322
    Prev
    Next
    INDEX
    Explanations

    casting Unity components

    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
     Wildcats
    0.55
    ⒎
    0.55
    Deposito
    0.54
    
    0.54
     האי
    0.54
     ﺍﻟ
    0.53
     ٹیک
    0.53
     manteniendo
    0.53
    鿌
    0.52
     feedstock
    0.52
    POSITIVE LOGITS
     C
    0.60
    stelle
    0.51
    κα
    0.48
    <strong>
    0.48
     disorderly
    0.47
    brain
    0.47
    ',
    0.46
    personas
    0.46
    U
    0.46
    쟁
    0.46
    Activations Density 0.008%

    No Known Activations