© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197022
    Prev
    Next
    INDEX
    Explanations

    leash or collar

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    feeds
    0.45
     feed
    0.43
     Schwartz
    0.43
     fodder
    0.41
     Sow
    0.40
    飼
    0.40
    furter
    0.40
     pens
    0.39
    Feeding
    0.39
    饲
    0.39
    POSITIVE LOGITS
    🇾
    0.45
     rope
    0.42
    旸
    0.42
    🇱
    0.42
     adjustable
    0.40
    Mill
    0.40
     strap
    0.40
    ण्य
    0.38
    ril
    0.38
    धारणा
    0.38
    Activations Density 0.001%

    No Known Activations