© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79679
    Prev
    Next
    INDEX
    Explanations

    build up

    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_31_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
     максимум
    0.20
     कहा
    0.19
    感谢
    0.19
    簪
    0.19
    帀
    0.18
     thanked
    0.18
     Primero
    0.18
     exchanging
    0.18
     сохранить
    0.18
    ㄕ
    0.18
    POSITIVE LOGITS
    ਾਂ
    0.21
     বিদেশী
    0.20
    接入
    0.20
    Threshold
    0.19
    ज़र
    0.18
    oppers
    0.18
     nodal
    0.18
     Trafford
    0.18
     Wirtschafts
    0.18
     들
    0.17
    Activations Density 0.001%

    No Known Activations