© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11531
    Prev
    Next
    INDEX
    Explanations

    law terminology and/or the word tort

    oai_token-act-pair · gemini-2.0-flash

    Legal and technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ed
    -1.23
    ever
    -0.88
    ist
    -0.86
    ists
    -0.84
    ized
    -0.82
    ian
    -0.81
    ised
    -0.81
    ey
    -0.79
     propOrder
    -0.78
    ib
    -0.76
    POSITIVE LOGITS
    t
    0.63
    __))
    0.54
    mybatisplus
    0.54
    tttt
    0.53
    heses
    0.52
    tin
    0.52
    tory
    0.50
    tan
    0.50
     OFDb
    0.49
    tance
    0.48
    Activations Density 15.102%

    No Known Activations