© 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. 58777
    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
    t
    1.54
    {
    1.45
     by
    1.41
     for
    1.07
     be
    1.00
    Y
    0.98
    ON
    0.96
    tı
    0.93
     are
    0.91
     at
    0.89
    POSITIVE LOGITS
    ри
    1.16
    ない
    1.04
    न
    1.04
    もっと
    1.02
    ни
    1.01
    きれい
    0.98
    行う
    0.98
    ૧
    0.98
    用の
    0.96
    ن
    0.95
    Activations Density 0.000%

    No Known Activations