© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126355
    Prev
    Next
    INDEX
    Explanations

    age description

    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_37_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
     swollen
    0.39
    ==-
    0.38
     roomy
    0.38
    具有
    0.38
     formatDate
    0.37
    ()<<
    0.37
     mogelijkheden
    0.37
     обстоятельства
    0.37
     circumstances
    0.37
     Chaplin
    0.37
    POSITIVE LOGITS
    rony
    0.40
     tortoises
    0.37
    ୌ
    0.37
    تی
    0.36
    িল
    0.36
    武
    0.36
     تا
    0.36
     emper
    0.35
     Alcal
    0.35
     bart
    0.35
    Activations Density 0.004%

    No Known Activations