© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144742
    Prev
    Next
    INDEX
    Explanations

    memo writing

    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_0_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
    ס
    2.25
    は
    1.87
    ন
    1.86
    a
    1.80
    ب
    1.79
    o
    1.77
    in
    1.76
    م
    1.70
    ו
    1.70
    ט
    1.70
    POSITIVE LOGITS
    ě
    1.26
    cription
    1.23
    irds
    1.16
    G
    1.14
    cesor
    1.05
    onym
    1.02
    rupted
    1.01
    kaan
    1.01
     جميلة
    1.01
    sembles
    1.00
    Activations Density 0.001%

    No Known Activations