© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10361
    Prev
    Next
    INDEX
    Explanations

    ASP.NET Web API

    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_40_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
     analyzers
    0.40
     stands
    0.37
     twin
    0.36
    ỡ
    0.36
    Disposition
    0.36
     bä
    0.35
     disappearance
    0.35
     genomes
    0.35
     dispositions
    0.35
    '])->
    0.35
    POSITIVE LOGITS
    TRACE
    0.41
    茈
    0.38
    リアル
    0.38
     MVC
    0.37
    owlapi
    0.36
    GraphQL
    0.36
    ZN
    0.36
     Tracey
    0.35
    ijkl
    0.35
    Syst
    0.35
    Activations Density 0.000%

    No Known Activations