© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    4. 148867
    Prev
    Next
    INDEX
    Explanations

    last sevenque coisathe East

    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_18_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
     peł
    0.54
     quản
    0.53
    “
    0.51
     gerenci
    0.51
     onları
    0.51
     aç
    0.50
     ఉంటాయి
    0.50
    ÇÕES
    0.50
    vvvert
    0.50
     actuators
    0.49
    POSITIVE LOGITS
    によって
    0.52
    必須
    0.49
    ود
    0.46
    憐
    0.44
    ською
    0.44
    нений
    0.43
    項
    0.43
    സ്ത
    0.43
    論文
    0.43
    われ
    0.42
    Activations Density 0.000%

    No Known Activations