© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113061
    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_2_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
    א
    1.14
     powied
    1.10
     дости
    1.00
    اك
    1.00
    :
    1.00
    إ
    1.00
    いを
    0.98
    astrar
    0.98
     비해
    0.98
    ри
    0.97
    POSITIVE LOGITS
    1.54
    .
    1.48
    ก็
    1.27
    ।
    1.17
    。
    1.13
    2
    1.11
    ，
    1.11
     at
    1.07
    פ
    1.05
    ני
    1.04
    Activations Density 0.000%

    No Known Activations