© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173892
    Prev
    Next
    INDEX
    Explanations

    assigns or equals

    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_20_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
    十一章
    0.45
     employment
    0.44
     гр
    0.44
     engagements
    0.43
    편
    0.43
     Employment
    0.43
    സ്വ
    0.43
     экземпля
    0.43
     commencement
    0.42
     झेल
    0.41
    POSITIVE LOGITS
     infert
    0.46
    ığınız
    0.45
    önig
    0.43
    erala
    0.43
     IOError
    0.41
    })=\
    0.41
     vua
    0.41
    चूर
    0.40
    ınıza
    0.40
     sebagainya
    0.40
    Activations Density 0.011%

    No Known Activations