© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166066
    Prev
    Next
    INDEX
    Explanations

    between moving parts

    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_31_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
     unten
    0.38
     மேற்பர
    0.35
     উত্তরাধ
    0.35
     Pastel
    0.34
    醾
    0.33
     pastel
    0.33
    ης
    0.33
    েক্টর
    0.33
    pastel
    0.32
    िरपेक्ष
    0.32
    POSITIVE LOGITS
     lem
    0.33
    InnerHTML
    0.32
     killed
    0.30
     mú
    0.30
    dealer
    0.30
    Dealer
    0.30
    ὠ
    0.29
    OCCO
    0.29
     dealer
    0.29
     spout
    0.29
    Activations Density 0.001%

    No Known Activations