© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207408
    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_20_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
    🤌
    0.50
    دە
    0.44
    இந்
    0.43
    GORITH
    0.43
     સિ
    0.42
     букмекердик
    0.42
    开关
    0.42
    优先级
    0.42
     سی
    0.42
     संके
    0.42
    POSITIVE LOGITS
     olive
    0.47
    한
    0.46
     fand
    0.41
    ¯
    0.41
    olive
    0.39
     छान
    0.39
     Olive
    0.38
     Zona
    0.38
     `
    0.38
     um
    0.38
    Activations Density 0.000%

    No Known Activations