© 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. 214888
    Prev
    Next
    INDEX
    Explanations

    system keywords

    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
     simonsen
    0.41
    傌
    0.38
     entrants
    0.38
    ruiter
    0.37
    솎
    0.37
     మె
    0.37
     Л
    0.36
     L
    0.35
     sağlı
    0.35
     Rok
    0.34
    POSITIVE LOGITS
     monoclonal
    0.44
    TD
    0.42
    êu
    0.40
     W
    0.39
    aita
    0.39
     VV
    0.39
    Edwards
    0.38
    Aux
    0.38
    Aub
    0.38
    Tiger
    0.38
    Activations Density 0.000%

    No Known Activations