© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34772
    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_3_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
    в
    1.21
    то
    1.17
    s
    1.09
    т
    1.02
    त
    1.01
    ת
    0.99
    с
    0.98
    ع
    0.98
    고
    0.93
    ні
    0.91
    POSITIVE LOGITS
    0.92
    ॉन
    0.80
    IS
    0.76
     Τ
    0.74
     masker
    0.70
    I
    0.70
     Φ
    0.69
    IRE
    0.68
    。)
    0.67
    ozer
    0.66
    Activations Density 0.000%

    No Known Activations