© 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. 53815
    Prev
    Next
    INDEX
    Explanations

    Serena Williams tennis player

    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
    傾
    0.40
    天气
    0.39
     দৈত্য
    0.38
     সমুদ্র
    0.37
    Cant
    0.37
     जर्म
    0.37
     পাখ
    0.36
     CANT
    0.36
     locking
    0.36
    continent
    0.36
    POSITIVE LOGITS
     ovarian
    0.46
    óg
    0.44
     hemod
    0.41
    妊
    0.41
     kobiet
    0.41
     mulheres
    0.40
    sg
    0.40
    łej
    0.39
     pregnancy
    0.39
     women
    0.38
    Activations Density 0.000%

    No Known Activations