© 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. 200567
    Prev
    Next
    INDEX
    Explanations

    **Right understanding and thought**

    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
     monks
    0.46
     monk
    0.43
    罟
    0.41
     prays
    0.40
     prayers
    0.40
     pray
    0.39
     молит
    0.39
     Prayers
    0.38
     Buddhist
    0.38
    ằm
    0.38
    POSITIVE LOGITS
    vin
    0.41
    惭
    0.38
    respected
    0.38
    スキル
    0.37
     Carb
    0.37
    mik
    0.37
    Vin
    0.36
     Dek
    0.36
     ধৈ
    0.36
    пар
    0.36
    Activations Density 0.001%

    No Known Activations