© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231202
    Prev
    Next
    INDEX
    Explanations

    tikz, shapes, blocks, node

    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
    로
    0.91
    ﻬ
    0.91
    ﻜ
    0.91
    ﻌ
    0.90
    ﻊ
    0.88
    ﮕ
    0.87
    ﻔ
    0.86
    ὃ
    0.83
     direta
    0.82
    ୱ
    0.81
    POSITIVE LOGITS
    on
    1.28
    ’
    1.19
     of
    0.98
     on
    0.97
    ai
    0.95
    <0x91>
    0.92
    ول
    0.91
     Import
    0.89
     Folder
    0.88
     was
    0.87
    Activations Density 0.001%

    No Known Activations