© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213659
    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_47_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
     desvent
    0.38
     berths
    0.37
    iennent
    0.37
     traps
    0.37
     civiles
    0.36
    --------------
    0.36
    ިޔ
    0.36
    υκ
    0.36
     LaserJet
    0.35
    icarboxylic
    0.35
    POSITIVE LOGITS
     دوا
    0.40
    erode
    0.37
     kinda
    0.37
     আন্দোল
    0.36
     Goshen
    0.36
     سادہ
    0.36
    }}{(
    0.36
    込んで
    0.36
     chon
    0.36
    谭
    0.36
    Activations Density 0.000%

    No Known Activations