© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98334
    Prev
    Next
    INDEX
    Explanations

    decode or bleeding

    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_16_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
     アメリカ
    0.52
     animaux
    0.50
    اوی
    0.49
    ارك
    0.49
    ا
    0.48
    וא
    0.48
     /[
    0.47
     primeiros
    0.47
     ሶ
    0.46
     utilisent
    0.46
    POSITIVE LOGITS
    ethical
    0.51
    obstacle
    0.50
    Lastly
    0.46
    critical
    0.46
    verkehr
    0.45
    View
    0.45
    storage
    0.45
    stände
    0.45
     Debate
    0.45
    ash
    0.45
    Activations Density 0.001%

    No Known Activations