© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207195
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    attributes
    0.40
    უთ
    0.38
    glicherweise
    0.38
     Spears
    0.38
    ares
    0.38
     않으면
    0.38
    ァ
    0.37
    itoa
    0.37
    ={[
    0.37
    pośred
    0.37
    POSITIVE LOGITS
     media
    0.43
     medium
    0.41
     Medium
    0.41
     स्टॉक
    0.38
     അഭിന
    0.38
     OLD
    0.38
     lust
    0.38
     heme
    0.37
    STOCK
    0.37
     SEQ
    0.37
    Activations Density 0.000%

    No Known Activations