© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210858
    Prev
    Next
    INDEX
    Explanations

    Chapter

    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_43_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
    conde
    0.36
    ఝ
    0.35
    сель
    0.35
    elte
    0.34
    ..</
    0.34
    塞尔
    0.34
    iculum
    0.34
    Ⅺ
    0.33
    ೃ
    0.33
     indexBuffer
    0.33
    POSITIVE LOGITS
     제목
    0.42
     title
    0.40
     Kev
    0.40
     titolo
    0.39
     intitul
    0.38
     मींस
    0.37
     검
    0.37
     титу
    0.37
     titular
    0.37
    Wiring
    0.37
    Activations Density 0.001%

    No Known Activations