© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79902
    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_0_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
     in
    1.35
    ム
    1.34
    I
    1.34
     ד
    1.33
    いた
    1.32
     hội
    1.30
    ラ
    1.30
     ה
    1.27
     pháp
    1.27
     kazi
    1.25
    POSITIVE LOGITS
    н
    1.92
    ти
    1.77
    ी
    1.65
    েও
    1.57
    ’
    1.56
    a
    1.51
    י
    1.43
    ло
    1.41
    n
    1.37
    ে
    1.37
    Activations Density 0.000%

    No Known Activations