© 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. 217527
    Prev
    Next
    INDEX
    Explanations

    cracked, fractured, or broken teeth

    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
    ﺪ
    0.55
     shorthand
    0.54
     blo
    0.54
     blood
    0.51
    ்ப்ப
    0.50
    ﺠ
    0.50
    ﺮ
    0.50
     Sudan
    0.49
    ment
    0.48
     कित
    0.48
    POSITIVE LOGITS
    Glowing
    0.58
     McDonalds
    0.55
    Cage
    0.53
    Inserting
    0.52
    Mount
    0.52
    Beware
    0.51
    🪵
    0.51
    🐵
    0.50
    Employer
    0.50
    ગવાન
    0.50
    Activations Density 0.001%

    No Known Activations