© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89389
    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_23_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
     Greeley
    0.41
     මත
    0.40
     എല്ലാം
    0.39
    稳定的
    0.39
    可能的
    0.38
    黙
    0.38
    实例
    0.38
    చిన
    0.37
    ﻡ
    0.37
     Creek
    0.37
    POSITIVE LOGITS
    many
    0.46
    zo
    0.41
    kha
    0.41
    binary
    0.41
    several
    0.41
    rothed
    0.40
    you
    0.39
    ဘ
    0.39
    Chess
    0.39
    inari
    0.39
    Activations Density 0.000%

    No Known Activations