© 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
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 195904
    Prev
    Next
    INDEX
    Explanations

    context questions

    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_26_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
    give
    0.22
     Gaya
    0.21
    Give
    0.20
    なった
    0.20
     XIA
    0.20
    }}},
    0.19
    filter
    0.19
    wash
    0.19
    ச்
    0.18
    wheels
    0.18
    POSITIVE LOGITS
    ргә
    0.20
    ᵁ
    0.19
     ประเทศ
    0.19
    EnglishMarks
    0.19
    یمپ
    0.19
    irá
    0.19
     Virgil
    0.19
     Jiménez
    0.18
    オリン
    0.18
    齧
    0.18
    Activations Density 0.010%

    No Known Activations