© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216455
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    苏
    0.41
     "?"]
    0.41
     Suck
    0.40
     lake
    0.40
     glacier
    0.39
    quetas
    0.39
     प्रतिदिन
    0.38
     aliquot
    0.38
    ベッド
    0.38
     Workbook
    0.37
    POSITIVE LOGITS
    arendra
    0.44
     Koenig
    0.44
    Charlotte
    0.43
    CHARLES
    0.43
    ull
    0.42
     샤
    0.42
    Charles
    0.40
    ).__
    0.39
     ราช
    0.39
    arang
    0.38
    Activations Density 0.000%

    No Known Activations