© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163525
    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_31_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
     expel
    0.37
     गु
    0.36
    codename
    0.36
     βο
    0.35
    嗪
    0.35
    uellement
    0.35
    很多人
    0.35
    ტორი
    0.34
     oś
    0.33
    StringVar
    0.33
    POSITIVE LOGITS
    -}
    0.41
     plumage
    0.40
    ínguez
    0.39
    শ্ত
    0.38
    ⌒
    0.38
     championships
    0.37
     مهمه
    0.37
    oyi
    0.36
    gpt
    0.36
    ništva
    0.36
    Activations Density 0.000%

    No Known Activations