© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141060
    Prev
    Next
    INDEX
    Explanations

    law firm names and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     solicitors
    0.52
    律师
    0.50
     attorneys
    0.48
     handlers
    0.48
     approxim
    0.48
     invertebrate
    0.47
    )=(
    0.47
     benthic
    0.47
     lawyers
    0.47
    iotic
    0.47
    POSITIVE LOGITS
     }
    0.54
    finden
    0.50
    Infrastructure
    0.48
    firebase
    0.48
    zzel
    0.47
    }_
    0.47
    INN
    0.46
    ედერ
    0.46
    াজার
    0.46
    innan
    0.46
    Activations Density 0.008%

    No Known Activations