© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194841
    Prev
    Next
    INDEX
    Explanations

    actress roles

    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_27_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
    ("\"
    0.37
     humanity
    0.37
     zegt
    0.37
    Hall
    0.36
    予測
    0.36
    ᅴ
    0.36
     hall
    0.36
    ATIC
    0.36
    (":
    0.35
    潛
    0.35
    POSITIVE LOGITS
    तोंडा
    0.36
     konc
    0.34
    打印
    0.34
    ondan
    0.34
    ழ்பெற்ற
    0.34
     print
    0.33
    vió
    0.33
    компа
    0.32
     Wor
    0.32
     reconhecimento
    0.32
    Activations Density 0.000%

    No Known Activations