© 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. 248694
    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
     odds
    0.38
    ソー
    0.37
    prex
    0.37
    ޯ
    0.37
    浱
    0.36
    obat
    0.36
    isode
    0.35
     apoy
    0.35
    ोरेंट
    0.35
    ोटी
    0.35
    POSITIVE LOGITS
     Anger
    0.41
     sketches
    0.41
    ائم
    0.40
     sagt
    0.39
     net
    0.38
     Carpet
    0.38
    净
    0.38
    Net
    0.37
    Liverpool
    0.37
     Jérôme
    0.37
    Activations Density 0.000%

    No Known Activations