© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183054
    Prev
    Next
    INDEX
    Explanations

    code variables or arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
    乐
    0.34
     Rim
    0.34
    选项
    0.34
    ark
    0.33
    是个
    0.33
     option
    0.33
    Ts
    0.32
    が登場
    0.32
    高性能
    0.31
     Ts
    0.31
    POSITIVE LOGITS
    ត់
    0.39
     착
    0.38
    лих
    0.38
    uve
    0.37
     imitating
    0.36
    姦
    0.36
     психи
    0.36
    けた
    0.35
     contemplating
    0.34
     jardins
    0.33
    Activations Density 0.017%

    No Known Activations