© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40884
    Prev
    Next
    INDEX
    Explanations

    gym and fitness activities

    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_11_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
    Node
    0.52
    สัย
    0.49
    Coat
    0.47
     بالس
    0.46
    (
    0.46
    я
    0.46
    And
    0.45
    Ag
    0.45
    Exception
    0.45
    VCTargetsPath
    0.45
    POSITIVE LOGITS
     Κ
    0.65
     окна
    0.61
     gyms
    0.60
    糺
    0.59
     черво
    0.58
     ELEMENTS
    0.57
     Ў
    0.56
     ચૂ
    0.56
    ⇉
    0.56
     огром
    0.55
    Activations Density 0.040%

    No Known Activations