© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165360
    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
    畛
    0.40
    Great
    0.38
     معیار
    0.38
    Caso
    0.36
    禽
    0.36
    inaan
    0.36
    цвет
    0.36
    ខ្ញ
    0.35
    皮膚
    0.35
    Fear
    0.35
    POSITIVE LOGITS
    ्व
    0.40
     უნდა
    0.38
    助
    0.38
     ਨਹੀਂ
    0.38
     leit
    0.37
     պատ
    0.37
     begin
    0.36
    ވަ
    0.36
     Burgund
    0.36
     Bagan
    0.36
    Activations Density 0.000%

    No Known Activations