© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27311
    Prev
    Next
    INDEX
    Explanations

    consulting a doctor

    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_10_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
     activer
    0.36
     shrinks
    0.36
     exclu
    0.36
     инде
    0.35
    ТЕ
    0.35
    К
    0.35
    doctor
    0.34
    doctors
    0.33
     for
    0.33
    bedrooms
    0.33
    POSITIVE LOGITS
    -
    0.31
    Id
    0.29
    ari
    0.29
    øn
    0.29
    िक
    0.28
    id
    0.28
    iv
    0.27
    á
    0.27
    ä
    0.27
     který
    0.27
    Activations Density 0.007%

    No Known Activations