© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41699
    Prev
    Next
    INDEX
    Explanations

    negotiate contracts or declare war

    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_22_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
     Kumb
    0.13
     furlough
    0.13
    тор
    0.13
    ை
    0.12
     Vez
    0.12
     praying
    0.12
     bumble
    0.12
     Wisdom
    0.12
     Fanny
    0.12
     Pess
    0.12
    POSITIVE LOGITS
     خارجية
    0.13
     investigated
    0.13
     investigaciones
    0.13
    postdata
    0.12
    畫
    0.12
     investigate
    0.12
    แบ่ง
    0.12
    積極的に
    0.12
    聯繫
    0.12
    ويت
    0.12
    Activations Density 0.007%

    No Known Activations