© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121805
    Prev
    Next
    INDEX
    Explanations

    cv2.COLOR_BGR2GRAY

    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_37_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
     stethoscope
    0.39
     tail
    0.39
     sale
    0.39
    Eye
    0.38
     bureaucratic
    0.38
    ("***
    0.38
    尾
    0.37
    Cement
    0.37
     lock
    0.36
     eye
    0.36
    POSITIVE LOGITS
     Sukh
    0.40
     причин
    0.40
     Inventor
    0.39
    न्दावन
    0.38
    icks
    0.37
     தெரியும்
    0.35
    银
    0.35
    Inventor
    0.35
     Rhône
    0.34
    сил
    0.34
    Activations Density 0.000%

    No Known Activations