© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169751
    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_56_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
    tained
    0.40
    ratto
    0.39
     க
    0.37
     wok
    0.36
    rarse
    0.36
     శు
    0.36
    ას
    0.35
    ulent
    0.35
    卷积
    0.35
    ark
    0.35
    POSITIVE LOGITS
    His
    0.41
     His
    0.41
    TMS
    0.38
    ().__
    0.38
    hpp
    0.38
    Οι
    0.37
     equi
    0.37
    qt
    0.36
     Specimens
    0.36
     kui
    0.36
    Activations Density 0.000%

    No Known Activations