© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159091
    Prev
    Next
    INDEX
    Explanations

    rabies concerns

    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
    a
    1.94
    า
    1.59
    া
    1.43
     {
    1.32
    o
    1.27
    ا
    1.26
    يد
    1.23
    p
    1.21
    c
    1.17
    or
    1.16
    POSITIVE LOGITS
    ’
    1.19
     spindles
    1.14
    ан
    1.05
    K
    1.03
     сайты
    1.00
    ants
    0.98
    ب
    0.96
    𝙷
    0.96
    кість
    0.95
    ushes
    0.93
    Activations Density 0.000%

    No Known Activations