© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192755
    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_4_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
    abor
    0.52
     כש
    0.46
    Depends
    0.46
    🙂
    0.46
    eras
    0.43
    ifica
    0.43
     במ
    0.43
     financiers
    0.43
    grayscale
    0.43
    É
    0.42
    POSITIVE LOGITS
    т
    0.79
    错
    0.58
    칭
    0.56
    解
    0.52
    景
    0.51
    、
    0.50
    模型
    0.50
    标记
    0.50
    ری
    0.50
     زیرمه
    0.49
    Activations Density 0.000%

    No Known Activations