© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206936
    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_19_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
     ه
    0.50
     incorporated
    0.50
     embroiled
    0.47
     اله
    0.45
    tól
    0.45
     intermin
    0.45
     imasmim
    0.44
     appended
    0.44
    خ
    0.44
     الات
    0.43
    POSITIVE LOGITS
     that
    0.50
     đó
    0.46
     तुल
    0.46
    ములో
    0.46
     venue
    0.44
    一次
    0.43
    门口
    0.43
    <>(
    0.42
    ೇಯ
    0.42
    场
    0.42
    Activations Density 0.000%

    No Known Activations