© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37307
    Prev
    Next
    INDEX
    Explanations

    CPU, modules, configuration, documentation

    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
    일
    0.61
    ίλ
    0.55
     జన్
    0.54
    र्थ
    0.53
     일
    0.53
     कैप
    0.50
    ześnie
    0.50
     있지
    0.50
     ഏറ്റ
    0.49
    ట్టిన
    0.49
    POSITIVE LOGITS
    t
    0.82
     sombre
    0.63
     Surve
    0.62
     doute
    0.58
    utente
    0.58
     altre
    0.55
     sweaty
    0.54
     working
    0.54
     sweat
    0.53
     aree
    0.53
    Activations Density 0.033%

    No Known Activations