© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197387
    Prev
    Next
    INDEX
    Explanations

    Manfred manifests version

    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_4_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
    ;
    1.04
    ার
    0.96
     I
    0.95
    ’
    0.93
    ो
    0.91
     i
    0.90
     y
    0.89
     decentral
    0.86
    ยิ่ง
    0.86
     environ
    0.82
    POSITIVE LOGITS
    l
    1.30
    ري
    1.27
    ل
    1.18
    k
    1.14
    ž
    1.09
    る
    1.06
    q
    1.01
    ت
    1.00
    تى
    0.97
    تك
    0.96
    Activations Density 0.001%

    No Known Activations