© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20357
    Prev
    Next
    INDEX
    Explanations

    brain parts

    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
    <td>
    0.53
     مقدس
    0.39
    চে
    0.38
    immer
    0.38
    ปลอดภัย
    0.36
    伌
    0.35
     उद्यमियों
    0.33
     ไหร่
    0.33
    Colombia
    0.33
     নাকের
    0.33
    POSITIVE LOGITS
     lim
    1.02
     pre
    1.00
     fore
    0.86
     fight
    0.80
     Pre
    0.78
    pre
    0.77
     प्री
    0.77
     Fore
    0.74
    预
    0.74
     Fight
    0.73
    Activations Density 0.038%

    No Known Activations