© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125532
    Prev
    Next
    INDEX
    Explanations

    country size and rank

    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_37_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
    ूज
    0.42
    看的
    0.39
     Seychelles
    0.38
     Heap
    0.36
    ັນ
    0.36
     Recol
    0.35
    庤
    0.35
     Trail
    0.35
     लर्न
    0.35
    缛
    0.35
    POSITIVE LOGITS
     geography
    1.59
     geographical
    1.52
     geograf
    1.52
     geographic
    1.48
     Geography
    1.41
    地理
    1.39
    Geography
    1.36
     географи
    1.35
     geographically
    1.34
     Geographical
    1.28
    Activations Density 0.085%

    No Known Activations