© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16819
    Prev
    Next
    INDEX
    Explanations

    man pages and options

    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_15_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
    回忆
    0.28
    !!!");
    0.28
    BuildContext
    0.26
    🫧
    0.26
    fog
    0.25
     sagt
    0.24
     پیچھے
    0.24
     crítico
    0.24
     نبود
    0.24
     say
    0.24
    POSITIVE LOGITS
    ק
    0.29
     radiographic
    0.29
    ের
    0.28
     में
    0.28
    на
    0.27
    лада
    0.26
    סה
    0.26
    এক
    0.25
    Мо
    0.25
     testname
    0.25
    Activations Density 0.012%

    No Known Activations