© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6519
    Prev
    Next
    INDEX
    Explanations

    living authentically

    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_39_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
    濮
    0.40
    ினை
    0.35
    Linking
    0.35
    丆
    0.34
     आपण
    0.33
    ِه
    0.33
    롬
    0.33
     thickness
    0.32
    ὲ
    0.32
    суль
    0.32
    POSITIVE LOGITS
     खरेदी
    0.39
    esten
    0.39
    Buy
    0.38
    ванный
    0.38
     RUB
    0.37
     живут
    0.37
     lived
    0.37
     కా
    0.36
    Urs
    0.36
     kup
    0.35
    Activations Density 0.018%

    No Known Activations