© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174407
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities or states

    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_20_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
    ucing
    0.29
    也会
    0.28
     Yourself
    0.25
    ention
    0.25
    iphone
    0.24
    也會
    0.24
    媜
    0.24
    ter
    0.24
    贞
    0.23
     yourself
    0.23
    POSITIVE LOGITS
     infinites
    0.23
     “
    0.21
     dì
    0.20
     rég
    0.20
     &=&
    0.20
     ≤
    0.20
     </
    0.20
     Tá
    0.20
     mét
    0.20
    வர்கள்
    0.20
    Activations Density 0.000%

    No Known Activations