© 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
    2. Gemma-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 51920
    Prev
    Next
    INDEX
    Explanations

    technology and services

    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_55_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
    .’”
    0.46
    '>"
    0.41
    —“
    0.39
     (“
    0.38
     “‘
    0.38
    ,’”
    0.36
    ?’”
    0.36
    ],'
    0.36
     “(
    0.36
     perí
    0.35
    POSITIVE LOGITS
    kyo
    0.52
    克斯
    0.52
    وسف
    0.51
    berg
    0.50
    bury
    0.49
    odore
    0.49
    INGTON
    0.48
    ೃಷ್ಣ
    0.48
    кса
    0.47
    쿄
    0.47
    Activations Density 0.025%

    No Known Activations