© 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. 220665
    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
    ůj
    0.38
    parks
    0.37
    ishly
    0.36
     DeL
    0.36
    ើរ
    0.36
     ancol
    0.35
     repris
    0.35
    ͠
    0.35
     rogue
    0.35
     Cytol
    0.35
    POSITIVE LOGITS
     بڑی
    0.37
     innervation
    0.36
    禦
    0.36
    Tact
    0.35
     **
    0.34
     paralys
    0.33
     Serial
    0.33
     $*
    0.32
    ңуз
    0.32
     copyspace
    0.32
    Activations Density 0.000%

    No Known Activations