© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226482
    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_10_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
    ᾗ
    0.55
     enfon
    0.55
    т
    0.55
    ت
    0.54
    ექ
    0.53
     denars
    0.52
    ﻓ
    0.51
    ﱠ
    0.51
    inicio
    0.51
    arli
    0.50
    POSITIVE LOGITS
     premier
    0.46
     bedside
    0.45
    ↵↵
    0.45
     Princeton
    0.44
     苏
    0.43
     Su
    0.43
     Block
    0.42
     block
    0.42
     Stanford
    0.41
     Serif
    0.41
    Activations Density 0.000%

    No Known Activations