© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15189
    Prev
    Next
    INDEX
    Explanations

    muscle definition

    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_40_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
    зия
    0.38
     жел
    0.37
     weighting
    0.36
     ಜೀವನ
    0.36
    ỡi
    0.36
    Whitespace
    0.36
    ombie
    0.36
    䘚
    0.36
    เซีย
    0.35
    ensin
    0.35
    POSITIVE LOGITS
     Definition
    1.70
    Definition
    1.62
     definition
    1.59
    definition
    1.44
    DEFINITION
    1.42
     definición
    1.34
     définition
    1.33
     Definitions
    1.30
     definição
    1.30
     definitions
    1.23
    Activations Density 0.090%

    No Known Activations