© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78773
    Prev
    Next
    INDEX
    Explanations

    country-capital pairs

    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_29_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
     ชั่วโมง
    0.35
    ('${
    0.34
     czter
    0.32
     republik
    0.32
     apuesta
    0.32
     automóvil
    0.32
     অভিনয়ের
    0.32
    வதில்
    0.32
     ሀ
    0.32
     trois
    0.31
    POSITIVE LOGITS
    Se
    0.30
    irc
    0.29
    DIY
    0.29
    IRC
    0.28
     detox
    0.28
     আসে
    0.27
    चक
    0.27
     জনক
    0.27
    erc
    0.27
     متخصص
    0.27
    Activations Density 0.006%

    No Known Activations