© 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. 170943
    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
     Slack
    0.50
     Siva
    0.49
     Ability
    0.48
     Moda
    0.47
     Capability
    0.46
    邾
    0.46
     Helper
    0.45
     Worse
    0.45
     IHDA
    0.45
     Help
    0.45
    POSITIVE LOGITS
    rooted
    0.45
     was
    0.45
     reapp
    0.45
     dawned
    0.44
    á
    0.44
     itself
    0.44
    architect
    0.44
     plán
    0.43
    after
    0.43
    infrastructure
    0.43
    Activations Density 0.000%

    No Known Activations