© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156651
    Prev
    Next
    INDEX
    Explanations

    electrical circuit

    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
    من
    1.13
     I
    1.12
    L
    1.09
    أ
    1.09
    h
    1.08
    U
    1.07
     T
    1.00
    是为了
    0.99
    ৫
    0.99
    ur
    0.98
    POSITIVE LOGITS
    ка
    1.46
    ك
    1.38
    кто
    1.27
    dı
    1.26
    ある
    1.25
    0
    1.23
    ק
    1.21
    ری
    1.19
    لی
    1.19
    ס
    1.17
    Activations Density 0.003%

    No Known Activations