© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17162
    Prev
    Next
    INDEX
    Explanations

    **ai**

    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_15_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
    k
    0.19
    table
    0.18
     different
    0.17
     honeycomb
    0.17
    ta
    0.17
    fic
    0.16
    “
    0.16
    f
    0.16
     unique
    0.16
    s
    0.16
    POSITIVE LOGITS
     Examining
    0.16
     kiedy
    0.16
    会儿
    0.16
     rutas
    0.15
     我的
    0.15
    奻
    0.15
     mensagens
    0.15
     hiyo
    0.15
     recounts
    0.15
     luyện
    0.14
    Activations Density 0.311%

    No Known Activations