© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122936
    Prev
    Next
    INDEX
    Explanations

    hot + beverage or food

    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_37_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
    zty
    0.39
    ตอน
    0.38
    览
    0.37
    hot
    0.37
     wives
    0.37
    পুরে
    0.37
     hot
    0.36
    wahati
    0.36
    hooting
    0.35
     Repairs
    0.35
    POSITIVE LOGITS
     sade
    0.40
    䉍
    0.40
    ళ్లు
    0.39
    effector
    0.38
    oksatta
    0.38
    والفق
    0.38
    Eugene
    0.38
     ezzel
    0.37
    Москва
    0.37
     Knee
    0.37
    Activations Density 0.002%

    No Known Activations