© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10537
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly found in legal documents

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    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
     des
    -0.47
     кӀош
    -0.45
     Pe
    -0.44
     pe
    -0.44
    sphin
    -0.41
     ped
    -0.40
     кӀ
    -0.40
     Digital
    -0.39
     Bag
    -0.38
     qu
    -0.37
    POSITIVE LOGITS
     الحره
    0.98
    zzleHttp
    0.84
     GenerationType
    0.83
    TagMode
    0.81
     HasFactory
    0.80
    SequentialGroup
    0.76
    +#+
    0.75
    HomeAsUpEnabled
    0.74
     {?}
    0.73
     дописавши
    0.73
    Activations Density 23.830%

    No Known Activations