© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101815
    Prev
    Next
    INDEX
    Explanations

    pain, urination, tenderness, light

    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_14_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
    _{
    0.54
    Starting
    0.49
    Evening
    0.48
    Verse
    0.47
    Forget
    0.47
    Ecommerce
    0.46
    July
    0.46
    ^{\
    0.45
    emony
    0.45
    Food
    0.45
    POSITIVE LOGITS
     वॉलेट
    0.56
     विद्यार्थ्या
    0.54
     能力
    0.50
    equity
    0.50
     calent
    0.50
     மாண
    0.49
     jdbc
    0.49
    最大の
    0.49
     traiter
    0.49
     ਗ
    0.49
    Activations Density 0.029%

    No Known Activations