© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14531
    Prev
    Next
    INDEX
    Explanations

    spoon

    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_15_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
    譞
    0.37
    相
    0.36
    in
    0.34
     할
    0.34
    财产
    0.34
    jz
    0.34
    Según
    0.34
     Round
    0.33
    erzo
    0.33
     칼
    0.33
    POSITIVE LOGITS
     двой
    0.40
     navigateur
    0.39
     kona
    0.38
    бар
    0.37
     рей
    0.37
     toen
    0.37
    𝙠
    0.36
    ادر
    0.35
     kik
    0.35
     swipes
    0.35
    Activations Density 0.029%

    No Known Activations