© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93588
    Prev
    Next
    INDEX
    Explanations

    userbankroll

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    9
    0.45
    8
    0.40
    澳门
    0.39
    7
    0.39
    放大
    0.38
    著
    0.38
    康
    0.38
    <u>
    0.37
    糖尿病
    0.37
    scht
    0.36
    POSITIVE LOGITS
    –
    0.62
    Į
    0.49
    --
    0.46
    RequestListener
    0.46
     ¥
    0.46
    하
    0.46
    į
    0.45
    --,
    0.44
    นั้น
    0.43
    ครั้ง
    0.43
    Activations Density 0.000%

    No Known Activations