© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211697
    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_20_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
    નમાં
    0.46
     speedily
    0.45
     veloce
    0.45
    ła
    0.44
     résistance
    0.44
     unwise
    0.44
     வேகமாக
    0.43
    芘
    0.43
     vehement
    0.43
    ikulum
    0.42
    POSITIVE LOGITS
    Differential
    0.48
    Manufacturers
    0.41
     USDC
    0.41
     manufacturers
    0.40
     professionals
    0.40
    出
    0.40
     diferenciales
    0.39
     subcontractors
    0.39
     Mailing
    0.39
    Insights
    0.39
    Activations Density 0.000%

    No Known Activations