© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 151613
    Prev
    Next
    INDEX
    Explanations

    "how many" or numbers

    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_23_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
     নিরপেক্ষ
    0.49
     फक्त
    0.45
    okay
    0.43
     tunnel
    0.42
    "});
    0.42
     planets
    0.42
     S
    0.42
     only
    0.41
     Kết
    0.41
     ADHD
    0.40
    POSITIVE LOGITS
    Although
    0.43
    იღ
    0.42
    thorace
    0.40
    скія
    0.40
    ابات
    0.39
     soliciting
    0.39
    .([]
    0.39
    Sullivan
    0.39
    ськ
    0.39
     സ്വദേശ
    0.39
    Activations Density 0.000%

    No Known Activations