© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260983
    Prev
    Next
    INDEX
    Explanations

    script commands

    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_22_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
    ঈদ
    0.24
     değişt
    0.22
    ɮ
    0.21
     проведе
    0.21
    Công
    0.20
     गुजरात
    0.20
     ชอบ
    0.20
    ości
    0.20
    ויות
    0.20
     কালী
    0.20
    POSITIVE LOGITS
     Tracy
    0.20
     \[
    0.20
     Shepard
    0.19
    cone
    0.19
    斛
    0.18
     fruits
    0.18
     far
    0.18
     {
    0.18
    மாகக்
    0.18
    haven
    0.18
    Activations Density 0.003%

    No Known Activations