© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231329
    Prev
    Next
    INDEX
    Explanations

    partial words for endings

    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_6_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
    ى
    1.20
     {
    1.00
     Э
    0.98
     Зна
    0.97
    1
    0.97
     Ве
    0.95
     Мер
    0.95
     Въ
    0.95
     Вер
    0.94
     Zwischen
    0.93
    POSITIVE LOGITS
    .
    1.38
    น
    1.10
    ਰ
    1.08
    IN
    1.02
    the
    1.02
    ING
    0.97
    มัน
    0.97
    لی
    0.94
    ین
    0.93
    AK
    0.92
    Activations Density 0.000%

    No Known Activations