© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36089
    Prev
    Next
    INDEX
    Explanations

    code syntax and related words

    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_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
     cristall
    0.42
     \%$,
    0.41
    滹
    0.41
     cristal
    0.39
     chronically
    0.39
     silicone
    0.38
     முத
    0.37
    dio
    0.36
     angered
    0.36
    [.
    0.36
    POSITIVE LOGITS
     sur
    0.43
    威尔
    0.39
     dangle
    0.38
     roulette
    0.37
    ানি
    0.36
     Dispatch
    0.35
     quảng
    0.34
    갬
    0.34
    桌面
    0.34
    Pend
    0.34
    Activations Density 0.040%

    No Known Activations