© 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. 149443
    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
     موارد
    0.44
    Deutschland
    0.41
    uttgart
    0.40
     पत्तियों
    0.40
    Mayor
    0.40
    orestation
    0.39
    utiérrez
    0.39
    桷
    0.39
    િસ
    0.39
    unnels
    0.39
    POSITIVE LOGITS
     Passion
    0.43
    ா
    0.40
     Attitude
    0.40
    рни
    0.39
     Kontext
    0.39
    hhh
    0.39
    kola
    0.39
     Feedback
    0.39
    ¥
    0.38
    <0xE0>
    0.38
    Activations Density 0.000%

    No Known Activations