© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129716
    Prev
    Next
    INDEX
    Explanations

    json keys: names, date, number, address

    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_25_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
     arugula
    0.23
    obbly
    0.21
     relive
    0.21
    Unlike
    0.20
    പ്പാ
    0.20
     clums
    0.20
    슭
    0.20
     素
    0.20
    arrows
    0.20
    MPC
    0.20
    POSITIVE LOGITS
     ambassador
    0.27
     বাক
    0.27
     видимо
    0.25
    킹
    0.24
    ля
    0.23
    दानी
    0.23
     Vocal
    0.22
    शिष्ट
    0.22
     kudos
    0.22
     recomand
    0.22
    Activations Density 0.005%

    No Known Activations