© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169899
    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_56_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
    놀
    0.33
    ViewState
    0.31
    Queen
    0.31
    UIT
    0.30
    iramente
    0.30
     Prés
    0.29
    ekš
    0.29
    lico
    0.28
    ="@+
    0.28
    去看
    0.28
    POSITIVE LOGITS
    -
    0.67
    ־
    0.55
    ‐
    0.42
    ‑
    0.40
     ছয়
    0.37
    ë
    0.37
     ä
    0.34
    ம்
    0.34
    ör
    0.33
    äh
    0.32
    Activations Density 0.000%

    No Known Activations