© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13677
    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_40_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
     îmb
    0.46
    ärast
    0.41
    ۾
    0.40
    の設定
    0.39
     कारखाना
    0.37
     setDefault
    0.37
    LAND
    0.36
    मोहन
    0.36
     कब्रिस्तान
    0.36
    ---------*/
    0.36
    POSITIVE LOGITS
     Chips
    0.37
     Nons
    0.37
     Cross
    0.37
     Adding
    0.36
     chips
    0.36
     adds
    0.36
    addTo
    0.36
     Matrix
    0.35
     Adds
    0.35
    Stake
    0.35
    Activations Density 0.000%

    No Known Activations