© 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. 130823
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    '
    1.59
    ’
    1.50
    _
    1.11
    -
    1.08
    Z
    1.03
    0.95
             
    0.88
    </h3>
    0.87
     Env
    0.86
     desliz
    0.85
    POSITIVE LOGITS
    in
    1.17
    تی
    0.97
    ढ़ाई
    0.90
    ні
    0.88
    ا۔
    0.88
    ן
    0.87
     campionato
    0.85
    daki
    0.84
    origine
    0.83
    дини
    0.83
    Activations Density 0.000%

    No Known Activations