© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196895
    Prev
    Next
    INDEX
    Explanations

    look at

    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_27_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
     Infrared
    0.36
     سق
    0.36
     Sing
    0.36
     Bxg
    0.35
    公司
    0.35
     thereof
    0.35
     बड़े
    0.35
     ಸ
    0.34
     свобо
    0.34
     свободы
    0.34
    POSITIVE LOGITS
    ারিং
    0.38
     meio
    0.37
    TGFuZ
    0.37
    ULATION
    0.36
    Running
    0.35
     maestra
    0.35
     símbolo
    0.34
    traf
    0.34
     penc
    0.34
    Clin
    0.34
    Activations Density 0.004%

    No Known Activations