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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138424
    Prev
    Next
    INDEX
    Explanations

    connection string

    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_37_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
    LEC
    0.41
    lant
    0.40
    нга
    0.38
    صف
    0.38
     Kish
    0.37
    alang
    0.37
    霊
    0.37
    result
    0.37
     Vitt
    0.37
    灵
    0.37
    POSITIVE LOGITS
     connection
    0.39
     conexión
    0.38
     CONNECTION
    0.38
    浓
    0.37
     WebDriver
    0.36
    ܝ
    0.36
     subscribe
    0.35
    ពេ
    0.35
     Verfü
    0.35
     kone
    0.35
    Activations Density 0.001%

    No Known Activations