© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132150
    Prev
    Next
    INDEX
    Explanations

    ses

    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_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
    Tai
    0.42
    ories
    0.41
     Su
    0.41
    Sal
    0.41
    alien
    0.40
    husky
    0.40
    era
    0.39
    란
    0.39
    su
    0.38
    Era
    0.38
    POSITIVE LOGITS
     downsizing
    0.43
    нци
    0.40
    卜
    0.39
    inck
    0.39
     पीओ
    0.38
    奭
    0.38
     آگ
    0.38
    izont
    0.38
     హి
    0.38
    цион
    0.37
    Activations Density 0.000%

    No Known Activations