© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65937
    Prev
    Next
    INDEX
    Explanations

    pretty

    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_46_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
     damn
    0.54
     functional
    0.45
    $}}
    0.44
     worse
    0.40
     darn
    0.40
     Damn
    0.39
    itational
    0.39
     mieux
    0.38
     denotes
    0.38
     pior
    0.38
    POSITIVE LOGITS
     privilege
    0.46
     стандарт
    0.41
     convict
    0.41
     überzeugt
    0.40
    DHL
    0.40
    ▋
    0.39
    boiler
    0.38
    жал
    0.38
     privilegi
    0.38
     Privilege
    0.38
    Activations Density 0.001%

    No Known Activations