© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134092
    Prev
    Next
    INDEX
    Explanations

    drowsy, sleepy, and tiredness

    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
     saveData
    0.43
    NuGetPackage
    0.38
     prolific
    0.38
    parad
    0.37
     parad
    0.37
     locally
    0.36
     DataFrame
    0.36
    焓
    0.35
     conservative
    0.35
    扡
    0.35
    POSITIVE LOGITS
    ঞ্চলে
    0.39
    दम
    0.38
    keydown
    0.38
    كتر
    0.38
     없습니다
    0.37
     обстоятельства
    0.37
    蹴
    0.37
    ूर्ति
    0.36
    噢
    0.36
    acly
    0.36
    Activations Density 0.002%

    No Known Activations