© 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. 14705
    Prev
    Next
    INDEX
    Explanations

    clothing fit

    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
    碧
    0.53
     external
    0.52
     vibrant
    0.51
    シ
    0.50
    バイ
    0.48
    ista
    0.47
     للد
    0.46
     anim
    0.45
     Brothers
    0.45
    ₤
    0.44
    POSITIVE LOGITS
     cinquième
    0.54
     नया
    0.53
    รุ่น
    0.53
     모델
    0.53
     neue
    0.52
     booting
    0.52
    窅
    0.51
     ครอง
    0.51
     రెండో
    0.49
     новую
    0.48
    Activations Density 0.022%

    No Known Activations