© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48816
    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_31_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
     bismuth
    0.40
     trauma
    0.40
    Pressure
    0.39
     unbalanced
    0.39
    ザ
    0.39
    नेशन
    0.37
    uera
    0.37
    Less
    0.36
    arashtra
    0.36
     Trauma
    0.36
    POSITIVE LOGITS
    ̆
    0.41
     behaviors
    0.35
     চালিয়ে
    0.35
    <0xBA>
    0.34
    施設
    0.34
    െല്ലാം
    0.34
     Portrait
    0.34
     마치
    0.33
     center
    0.33
     Grec
    0.33
    Activations Density 0.000%

    No Known Activations