© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 198124
    Prev
    Next
    INDEX
    Explanations

    job titles

    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
    Analy
    0.43
     analyt
    0.41
    நப
    0.39
     symptomatic
    0.39
    "}}>
    0.39
    纰
    0.38
     Analytical
    0.38
     Analytic
    0.38
    稷
    0.38
    Analytical
    0.37
    POSITIVE LOGITS
     কব
    0.45
    lage
    0.41
     Ward
    0.41
     bel
    0.40
    ripción
    0.39
     BEL
    0.39
     spit
    0.38
    berries
    0.38
    mins
    0.38
     ofici
    0.38
    Activations Density 0.005%

    No Known Activations