© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10217
    Prev
    Next
    INDEX
    Explanations

    things related to photo credits and legal entities, often including names and company types like "Insurance Company".

    oai_token-act-pair · gemini-2.0-flash

    Legal and financial matters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ValueStyle
    -0.85
     ModelExpression
    -0.78
    ConstraintMaker
    -0.64
     intptr
    -0.64
    NameInMap
    -0.61
     CreateTagHelper
    -0.61
    Parcelize
    -0.59
     мәкал
    -0.58
     ostavi
    -0.58
     aapt
    -0.58
    POSITIVE LOGITS
    .*")]
    0.59
    Matty
    0.54
     Baumwolle
    0.48
     Valentín
    0.48
    Brexit
    0.47
     HART
    0.47
    ]').
    0.46
    Примечания
    0.46
     Bie
    0.45
     "").
    0.45
    Activations Density 0.780%

    No Known Activations