© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156195
    Prev
    Next
    INDEX
    Explanations

    say "complete" words

    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_50_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
     Trigon
    0.40
     Cousin
    0.40
    cubic
    0.38
    ǜ
    0.38
     Flaxman
    0.37
    aupun
    0.37
    Sir
    0.36
     quarks
    0.35
     cofactor
    0.35
    ANCIS
    0.35
    POSITIVE LOGITS
    Complete
    1.38
     Complete
    1.36
     complet
    1.32
     Comple
    1.32
    Comple
    1.29
     complete
    1.27
    complete
    1.25
     completo
    1.24
    完
    1.24
     completa
    1.22
    Activations Density 0.001%

    No Known Activations