© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121804
    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_37_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
    ্টার
    0.41
    풍
    0.38
    モニター
    0.37
     Kid
    0.36
     Monitor
    0.35
     kidnapped
    0.35
    ంటీ
    0.35
     Koh
    0.35
     comfortably
    0.34
     rotator
    0.34
    POSITIVE LOGITS
    殺
    0.84
     kills
    0.82
     kill
    0.80
    杀
    0.78
     killing
    0.78
    killing
    0.77
    杀死
    0.76
    杀了
    0.73
    kill
    0.73
     killed
    0.71
    Activations Density 0.000%

    No Known Activations