© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49424
    Prev
    Next
    INDEX
    Explanations

    weight management drugs

    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_31_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
     sweetness
    0.43
     bathing
    0.41
     risotto
    0.40
     sourdough
    0.40
     bathe
    0.40
     molasses
    0.39
    醗
    0.39
     నె
    0.38
     canola
    0.38
     gamm
    0.38
    POSITIVE LOGITS
    艿
    0.47
    prescription
    0.42
    viii
    0.41
     सहायक
    0.40
    噻
    0.40
    助
    0.38
     Obst
    0.37
    획
    0.37
     filled
    0.37
     enclosure
    0.37
    Activations Density 0.002%

    No Known Activations