© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45694
    Prev
    Next
    INDEX
    Explanations

    Counter trade

    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_10_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
    ーン
    0.17
    ን
    0.17
    الف
    0.16
    льника
    0.16
    ﺖ
    0.15
     communément
    0.15
    ون
    0.15
    셍
    0.15
    뇰
    0.15
     öffentlichen
    0.14
    POSITIVE LOGITS
     counter
    0.20
    "
    0.17
    on
    0.17
    ization
    0.17
     wares
    0.16
     Counter
    0.15
    ritt
    0.15
     countering
    0.15
    ri
    0.15
    ag
    0.15
    Activations Density 0.001%

    No Known Activations