© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233288
    Prev
    Next
    INDEX
    Explanations

    Ukraine transit, export, inflation

    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_32_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
    Gren
    0.33
    Mem
    0.31
    <{},
    0.30
     derivable
    0.30
    directory
    0.29
    Tend
    0.29
     grenades
    0.29
     natively
    0.28
     cartridges
    0.28
     neige
    0.28
    POSITIVE LOGITS
    怼
    0.36
    陥
    0.35
    抠
    0.34
    ствия
    0.33
     گیری
    0.33
     الحالي
    0.32
     হইল
    0.31
     アイアン
    0.31
     JOHN
    0.31
    arbeitet
    0.31
    Activations Density 0.001%

    No Known Activations