© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6490
    Prev
    Next
    INDEX
    Explanations

    legal and corporate jargon related to judgements, appeals, reports, and testimonies.

    oai_token-act-pair · gemini-2.0-flash

    refer

    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
     فريبيس
    -0.69
    saying
    -0.64
    ########.
    -0.63
    Says
    -0.57
     beit
    -0.56
    isContained
    -0.56
    
    -0.55
     décrire
    -0.55
    Said
    -0.54
     Describes
    -0.54
    POSITIVE LOGITS
     refer
    1.02
     reference
    0.95
     referred
    0.87
     refers
    0.86
     Refer
    0.83
     Reference
    0.80
    Refer
    0.79
    refer
    0.78
     REFERENCE
    0.77
     references
    0.73
    Activations Density 4.573%

    No Known Activations