© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92822
    Prev
    Next
    INDEX
    Explanations

    caveat

    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_11_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
    كس
    0.65
    נת
    0.59
     wasn
    0.57
    n
    0.56
     Appalachian
    0.55
     उप
    0.54
     zariaden
    0.54
    පා
    0.52
     Class
    0.52
     длин
    0.52
    POSITIVE LOGITS
     fraud
    0.64
     fraudsters
    0.62
    。
    0.59
     harming
    0.56
     tinct
    0.55
     millions
    0.55
    ために
    0.54
    rictions
    0.54
     magistrates
    0.54
     frauds
    0.54
    Activations Density 0.000%

    No Known Activations