© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203458
    Prev
    Next
    INDEX
    Explanations

    on all fours / Rube Goldberg

    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_6_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
    '
    0.93
    ัน
    0.80
    <0x0D>
    0.77
    الإ
    0.77
    ון
    0.75
     werd
    0.72
    ﻱ
    0.71
    '};
    0.70
     aventure
    0.69
     conm
    0.68
    POSITIVE LOGITS
    ன்ஸ்
    0.74
    thed
    0.71
    extremely
    0.70
     -
    0.69
    t
    0.69
     semifinal
    0.68
    theta
    0.66
     Wanderers
    0.66
     luscious
    0.66
    lgende
    0.66
    Activations Density 0.000%

    No Known Activations