© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49714
    Prev
    Next
    INDEX
    Explanations

    big

    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_55_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
     epitope
    0.36
    𝙔
    0.35
     pesticide
    0.35
    ുകൂ
    0.35
     hydrant
    0.35
     fungicide
    0.34
     Insider
    0.34
    씁
    0.33
     заболе
    0.33
    чок
    0.33
    POSITIVE LOGITS
     big
    0.60
    big
    0.59
    BIG
    0.47
    Tray
    0.41
    夆
    0.38
     inn
    0.38
     tray
    0.37
     поне
    0.37
     box
    0.37
    とにかく
    0.37
    Activations Density 0.017%

    No Known Activations