© 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. 1609
    Prev
    Next
    INDEX
    Explanations

    res.send or res.json

    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
     MNIST
    0.43
     munc
    0.40
    MNIST
    0.38
    oclaw
    0.38
    RNAs
    0.38
    甾
    0.37
    денциа
    0.36
    atenate
    0.36
    طلاب
    0.36
    stacks
    0.36
    POSITIVE LOGITS
    Character
    0.39
    BLY
    0.38
    Type
    0.38
    駁
    0.38
    इसमें
    0.38
    خل
    0.38
    చె
    0.37
    Perform
    0.36
    chro
    0.36
     Type
    0.35
    Activations Density 0.002%

    No Known Activations