© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9169
    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_13_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
     Palestinians
    0.46
    isque
    0.44
     bot
    0.43
    但
    0.42
     vertical
    0.42
     pesca
    0.42
     WordPress
    0.41
    fers
    0.41
     barbers
    0.41
     aiming
    0.41
    POSITIVE LOGITS
     書い
    0.56
     ましょう
    0.53
    лари
    0.52
     美国
    0.52
     자
    0.51
    ಲಿಯ
    0.51
    ənd
    0.50
     빼
    0.50
    Ꮶ
    0.50
     tagReport
    0.49
    Activations Density 0.000%

    No Known Activations