© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    4. 81920
    Prev
    Next
    INDEX
    Explanations

    explain concepts

    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_0_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
    то
    0.56
    고
    0.54
    ناد
    0.53
    ه
    0.52
     गाड़ी
    0.50
    ри
    0.50
    都
    0.50
    are
    0.49
     odors
    0.49
     Collectors
    0.49
    POSITIVE LOGITS
     necessário
    0.66
    clickView
    0.62
    Ix
    0.61
     relacion
    0.57
     relaciona
    0.54
     downlink
    0.52
     nécessaires
    0.51
     concentra
    0.51
    🛂
    0.51
    ﺛ
    0.51
    Activations Density 0.000%

    No Known Activations