© 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-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4600
    Prev
    Next
    INDEX
    Explanations

    law firms paired with names and legal terms

    oai_token-act-pair · gemini-2.0-flash

    legal firms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISNI
    -0.52
    Pozri
    -0.49
    IALLY
    -0.49
    SaveChangesAsync
    -0.47
     Bohn
    -0.47
    $",
    -0.46
     Neff
    -0.46
    $")
    -0.46
    ndorf
    -0.45
     berjalan
    -0.45
    POSITIVE LOGITS
     firm
    0.86
     firms
    0.81
    firm
    0.70
     FIRM
    0.69
     Firm
    0.69
     Firms
    0.69
    Firm
    0.68
     &
    0.63
     firma
    0.63
    Fir
    0.61
    Activations Density 0.455%

    No Known Activations