© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35326
    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_31_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
    Mean
    0.37
    }}^{(
    0.37
     Selv
    0.36
    自
    0.35
     kör
    0.35
    issances
    0.35
    Megan
    0.35
    癲
    0.35
    ottam
    0.35
    files
    0.35
    POSITIVE LOGITS
     CUT
    0.37
     historically
    0.36
    inum
    0.36
     elderly
    0.36
     signatories
    0.35
     ubiqu
    0.35
    fted
    0.35
     peanuts
    0.35
     difficulty
    0.35
     pancreas
    0.34
    Activations Density 0.000%

    No Known Activations