© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159323
    Prev
    Next
    INDEX
    Explanations

    Agda, Idris, Coq dependent types

    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_2_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
    ן
    1.59
    ot
    1.33
    ك
    1.24
    ق
    1.18
    نا
    1.12
    ون
    1.06
    ↵↵
    1.05
    N
    0.98
    ا
    0.98
    lige
    0.97
    POSITIVE LOGITS
     молодо
    1.05
     εται
    1.03
     roku
    1.02
     nourished
    1.00
     κι
    0.96
     saludable
    0.96
     maliciously
    0.95
     devoured
    0.94
     malicious
    0.93
     이미
    0.92
    Activations Density 0.000%

    No Known Activations