© 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. 201842
    Prev
    Next
    INDEX
    Explanations

    RDF, SPARQL, OWL

    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
    ばん
    0.40
    Código
    0.38
    琥
    0.37
    olidated
    0.35
    Ĩ
    0.35
     தாம்
    0.35
    stir
    0.35
    raded
    0.34
    廳
    0.34
    徽
    0.34
    POSITIVE LOGITS
     SPAR
    0.84
     RDF
    0.71
     spar
    0.64
    RDF
    0.64
     owl
    0.60
     Owl
    0.60
     Spar
    0.60
     rdf
    0.59
    Spar
    0.57
     Graph
    0.57
    Activations Density 0.002%

    No Known Activations