© 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. 162752
    Prev
    Next
    INDEX
    Explanations

    manufacturer or supplier

    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
    ⁾
    0.41
    喜剧
    0.40
    TaskPojo
    0.39
    Harold
    0.38
    варти
    0.37
    ホテル
    0.37
     houseboat
    0.37
    民宿
    0.36
     ОО
    0.36
    烀
    0.36
    POSITIVE LOGITS
     bitter
    0.42
     তিক্ত
    0.38
     sitä
    0.38
     dedication
    0.37
     Selling
    0.37
    elos
    0.37
     hinges
    0.36
     nahil
    0.36
     ষষ্ঠ
    0.36
     dos
    0.36
    Activations Density 0.000%

    No Known Activations