© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 473
    Prev
    Next
    INDEX
    Explanations

    places and programming concepts

    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_40_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
     anunci
    0.42
    Ȧ
    0.39
     enunciado
    0.38
    儿童
    0.37
    љашње
    0.37
     mexicano
    0.36
    ediaan
    0.36
     announcing
    0.35
    中华人民共和国
    0.35
    ยนตร์
    0.35
    POSITIVE LOGITS
    禍
    0.40
     ща
    0.38
    dsl
    0.38
     taim
    0.38
    ウェア
    0.37
     Martyn
    0.37
    行った
    0.37
     obliged
    0.36
     mdl
    0.36
    েষ
    0.35
    Activations Density 0.003%

    No Known Activations