© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242440
    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_40_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
    पट
    0.37
    tych
    0.37
    Tom
    0.37
     لوبی
    0.37
    Rounded
    0.36
     Rounded
    0.35
    惕
    0.35
     Tom
    0.35
     می‌کند
    0.35
    Batch
    0.34
    POSITIVE LOGITS
    牯
    0.45
    楦
    0.42
     reward
    0.41
     sistema
    0.41
     diffe
    0.41
    utilisation
    0.40
     utilisation
    0.39
     tradizione
    0.39
     système
    0.38
    خراج
    0.38
    Activations Density 0.000%

    No Known Activations