© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91721
    Prev
    Next
    INDEX
    Explanations

    miscellaneous fragments

    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_60_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
    ↵↵
    0.91
    ↵
    0.78
    <start_of_image>
    0.66
    <0xE3>
    0.64
    ‬
    0.63
    </h2>
    0.63
    0.58
    <0x0D>
    0.57
    0.54
    </h3>
    0.53
    POSITIVE LOGITS
    unches
    0.40
    प्ताहिक
    0.40
    attham
    0.40
     ಸಿ
    0.40
    ovll
    0.39
    issant
    0.39
    çe
    0.39
    attutto
    0.39
     দিয়াছেন
    0.38
    ಂಡ್
    0.38
    Activations Density 0.009%

    No Known Activations