© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107663
    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_2_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
    ン
    1.20
    ن
    1.11
    ü
    1.02
    ных
    0.98
    ری
    0.98
    ان
    0.92
     Gibbons
    0.91
    an
    0.91
    其他
    0.89
     to
    0.89
    POSITIVE LOGITS
    ли
    1.27
    ти
    1.25
    (
    1.15
    も
    1.15
    ある
    1.09
    of
    1.07
    σε
    1.07
    ट
    1.07
    ции
    1.06
    る
    1.05
    Activations Density 0.000%

    No Known Activations