© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45344
    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_22_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
     Better
    0.40
     Up
    0.39
     we
    0.38
    Up
    0.38
     statue
    0.37
     grateful
    0.36
    ب
    0.35
     sr
    0.35
     acquaintance
    0.35
     up
    0.34
    POSITIVE LOGITS
    θούν
    0.42
     funzionamento
    0.39
    chrane
    0.37
    سترول
    0.37
    inery
    0.36
     véritables
    0.36
    ijų
    0.36
    Invalids
    0.36
    Setpoint
    0.36
    lycer
    0.35
    Activations Density 0.000%

    No Known Activations