© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229534
    Prev
    Next
    INDEX
    Explanations

    locations and cities

    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_57_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
    ékek
    0.45
    iteit
    0.40
    ме
    0.40
    iste
    0.40
    umé
    0.39
    eleaf
    0.39
    缢
    0.38
    ေသ
    0.38
    WUE
    0.37
     entering
    0.37
    POSITIVE LOGITS
     bin
    0.37
     ghar
    0.35
     बरत
    0.35
    innam
    0.34
     degrade
    0.33
     locations
    0.32
    ğan
    0.32
     hvor
    0.32
     cautious
    0.32
     সন্
    0.32
    Activations Density 0.000%

    No Known Activations