© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206988
    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_20_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
    cruise
    0.51
    ച
    0.47
     mögliche
    0.45
    cially
    0.44
     Corbett
    0.44
     Ivan
    0.44
    ウド
    0.44
    h
    0.44
    ería
    0.43
     رکھے
    0.43
    POSITIVE LOGITS
     parole
    0.48
     decre
    0.48
    Alors
    0.47
     parasites
    0.45
     bourgeois
    0.45
    agos
    0.44
     strCmd
    0.44
     playerCards
    0.44
     이후
    0.44
     glared
    0.43
    Activations Density 0.000%

    No Known Activations