© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3977
    Prev
    Next
    INDEX
    Explanations

    early 20th century history

    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_39_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
     রাধানাথ
    0.51
     १८४
    0.41
    irmeye
    0.39
    dimensioni
    0.38
    processor
    0.38
    '])[
    0.38
    ">[
    0.37
    (%
    0.37
    १८६
    0.37
     informed
    0.36
    POSITIVE LOGITS
     motor
    0.48
     ১৯
    0.45
     automobile
    0.44
     Motor
    0.44
     wireless
    0.43
     postcard
    0.43
     chauffeur
    0.42
     Taft
    0.42
     ১৩২১
    0.41
    iman
    0.40
    Activations Density 0.041%

    No Known Activations