© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130057
    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_6_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
    า
    0.96
    to
    0.90
     自
    0.88
     它
    0.87
     כדי
    0.87
     对
    0.86
    ,
    0.82
     déclare
    0.82
    ↵↵
    0.81
     ก็
    0.80
    POSITIVE LOGITS
    ре
    1.18
    ers
    0.91
    ра
    0.90
    য়ের
    0.90
    ent
    0.89
    ों
    0.89
    ги
    0.89
    रा
    0.88
    ंनी
    0.85
    ere
    0.83
    Activations Density 0.000%

    No Known Activations