© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68254
    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_46_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
    NaOH
    0.42
    बू
    0.41
    pH
    0.41
    PTO
    0.41
     бай
    0.39
    軸
    0.38
     ढक
    0.38
     रहेंगे
    0.38
    ビア
    0.38
     топо
    0.38
    POSITIVE LOGITS
    ille
    0.38
     eder
    0.36
    "[
    0.36
     "./
    0.35
     DEV
    0.35
     waw
    0.35
     ምክንያት
    0.35
     ("[
    0.34
    udev
    0.34
    hluk
    0.34
    Activations Density 0.000%

    No Known Activations