© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63344
    Prev
    Next
    INDEX
    Explanations

    uniform

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    บั
    0.46
    ὼ
    0.38
    eared
    0.34
    idian
    0.34
    スタル
    0.34
    anais
    0.33
    STIC
    0.33
    irai
    0.33
    莲
    0.33
    ogly
    0.33
    POSITIVE LOGITS
     uniform
    3.72
     Uniform
    3.69
    Uniform
    3.59
    uniform
    3.45
     uniforme
    3.19
     uniformly
    3.05
     uniformity
    3.03
     uniforms
    2.77
    uniformly
    2.73
    均匀
    2.55
    Activations Density 0.164%

    No Known Activations