© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31456
    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_7_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
     manier
    0.45
    <start_of_image>
    0.43
    akas
    0.43
     Have
    0.42
     Retrieves
    0.42
    淏
    0.42
     Contact
    0.41
    υτό
    0.41
     Besides
    0.41
    [["
    0.40
    POSITIVE LOGITS
     ന്
    0.54
     saddle
    0.52
     artich
    0.51
     کہہ
    0.51
     ಸಾಮಾನ್ಯವಾಗಿ
    0.51
     profissional
    0.50
     $%
    0.49
     झाली
    0.49
     ian
    0.48
     çağ
    0.47
    Activations Density 0.000%

    No Known Activations