© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152955
    Prev
    Next
    INDEX
    Explanations

    capital Territory

    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_23_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
    zj
    0.30
     considérable
    0.28
     '*')
    0.28
     iniziamo
    0.28
    epi
    0.28
    स्ती
    0.28
    BeforeCall
    0.27
     vody
    0.27
     décidé
    0.26
     zů
    0.26
    POSITIVE LOGITS
    lation
    0.30
    如果你
    0.29
    同樣
    0.29
     Neolithic
    0.28
     Intelligence
    0.28
    -
    0.28
    itized
    0.27
    騏
    0.27
     intelig
    0.27
     bottlenecks
    0.27
    Activations Density 0.067%

    No Known Activations