© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179111
    Prev
    Next
    INDEX
    Explanations

    contrary, protective, allowed, liability, contingent

    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_29_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
     apparaître
    0.39
    лишком
    0.39
    зили
    0.38
     бюд
    0.38
     Ausnahme
    0.38
     hinsichtlich
    0.37
     इसीलिए
    0.37
    ㄡ
    0.37
     İstanbul
    0.36
     व्यावहारिक
    0.36
    POSITIVE LOGITS
     取
    0.40
     inflam
    0.38
    取
    0.37
    lens
    0.37
    Trader
    0.37
    agus
    0.36
     inflammatory
    0.36
    with
    0.36
    خذ
    0.35
    គ្រ
    0.35
    Activations Density 0.000%

    No Known Activations