© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78289
    Prev
    Next
    INDEX
    Explanations

    blog

    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_53_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
    poles
    0.43
    fores
    0.43
    ويس
    0.43
    ষুধ
    0.41
    postos
    0.40
     basins
    0.39
    艳
    0.39
    phus
    0.39
    ppet
    0.38
    Scopes
    0.38
    POSITIVE LOGITS
    ᱩ
    0.37
     Agreement
    0.37
     ontology
    0.37
    sı
    0.37
     geom
    0.37
     çalışmaları
    0.36
    ections
    0.35
    unpkg
    0.35
     monologue
    0.35
    ाल
    0.35
    Activations Density 0.003%

    No Known Activations