© 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. 110134
    Prev
    Next
    INDEX
    Explanations

    APA citations and formatting

    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
    -
    1.32
    ía
    1.04
    خدام
    1.02
    '
    0.99
    ación
    0.95
    (
    0.93
    ิง
    0.92
     that
    0.90
    ént
    0.89
    ă
    0.88
    POSITIVE LOGITS
    на
    1.52
    ро
    1.49
    ма
    1.48
    त
    1.45
    ম
    1.39
    ور
    1.37
    ل
    1.27
    ки
    1.25
    res
    1.23
    ،
    1.21
    Activations Density 0.001%

    No Known Activations