© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3615
    Prev
    Next
    INDEX
    Explanations

    phrases that are related to court, law and legal documents

    oai_token-act-pair · gemini-2.0-flash

    material

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personensuche
    -0.69
     跳转至
    -0.63
    Filmografie
    -0.60
    stdc
    -0.57
    TagMode
    -0.54
     endwhile
    -0.52
    <?>>
    -0.52
     Signalez
    -0.51
     CURIAM
    -0.51
    ngdoc
    -0.50
    POSITIVE LOGITS
     material
    2.36
    material
    2.11
     MATERIAL
    1.95
     Material
    1.94
    Material
    1.88
    MATERIAL
    1.66
     materiale
    1.50
     materiales
    1.32
     materiaal
    1.30
     материал
    1.24
    Activations Density 9.747%

    No Known Activations