© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12002
    Prev
    Next
    INDEX
    Explanations

    legal language related to trusts, beneficiaries, and estates

    oai_token-act-pair · gemini-2.0-flash

    legal documents and trusts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    lapsingToolbar
    -0.51
     domestiques
    -0.51
     Draper
    -0.49
    Bissau
    -0.49
     électron
    -0.48
    liptical
    -0.48
    ształ
    -0.48
     Transitional
    -0.47
     rentrée
    -0.46
    serialization
    -0.45
    POSITIVE LOGITS
    contentLoaded
    0.71
     ostavi
    0.66
    OGND
    0.64
     Италијани
    0.63
    featureID
    0.63
     trust
    0.61
    XtraReports
    0.59
     незавершена
    0.59
    </tfoot>
    0.59
     ExecuteAsync
    0.59
    Activations Density 3.720%

    No Known Activations