© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203535
    Prev
    Next
    INDEX
    Explanations

    fuel injector

    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_12_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
     масло
    0.63
     allClasses
    0.56
     इंपॉर्ट
    0.54
     klik
    0.52
     یکی
    0.52
     контакта
    0.52
    乑
    0.52
    Novo
    0.52
     Förderung
    0.50
     масла
    0.50
    POSITIVE LOGITS
    racellular
    0.59
    rise
    0.50
    rage
    0.50
    一時
    0.49
    衰
    0.49
     temporarily
    0.48
     ಪರಿಸ
    0.48
    rai
    0.48
    ]{
    0.47
    消費
    0.47
    Activations Density 0.001%

    No Known Activations