© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63787
    Prev
    Next
    INDEX
    Explanations

    docker-compose version: 3.8 or 3.9

    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_41_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
     샘
    0.40
    漲
    0.40
    균
    0.39
     равномер
    0.38
    byn
    0.38
    난
    0.36
    ränkt
    0.36
     চরণ
    0.36
    Bounce
    0.36
    涨
    0.36
    POSITIVE LOGITS
     vector
    0.43
    iiv
    0.42
     membrane
    0.39
     protocol
    0.38
     trimming
    0.37
     job
    0.37
     Jim
    0.37
    emplo
    0.37
     preg
    0.36
     times
    0.36
    Activations Density 0.000%

    No Known Activations