© 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. 201194
    Prev
    Next
    INDEX
    Explanations

    pillow or pillows

    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
     obsahuje
    0.42
     contient
    0.42
     contenant
    0.40
     /[
    0.39
     stuffed
    0.38
     contenir
    0.38
     truncated
    0.38
     содержит
    0.38
     contains
    0.38
     containing
    0.37
    POSITIVE LOGITS
     respectful
    0.41
    ˢ
    0.39
    ihydro
    0.38
     HRS
    0.38
     Fingers
    0.38
     tình
    0.38
     Interiors
    0.38
     Corrosion
    0.37
    が行
    0.37
    噔
    0.37
    Activations Density 0.000%

    No Known Activations