© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3483
    Prev
    Next
    INDEX
    Explanations

    dedicated

    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_44_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
    िनियम
    0.40
     юм
    0.37
    渚
    0.37
     ore
    0.37
    стьян
    0.36
     midnight
    0.36
    гация
    0.36
     गज
    0.35
    攪
    0.35
     stir
    0.35
    POSITIVE LOGITS
     devoted
    2.69
     dedicated
    2.42
     devote
    2.33
     dedic
    2.17
     dedicado
    2.17
    dedicated
    2.17
     dedicate
    2.16
     dedicada
    2.13
    Dedicated
    2.11
     dedicato
    2.09
    Activations Density 0.269%

    No Known Activations