© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8025
    Prev
    Next
    INDEX
    Explanations

    legal citations including "rule," "court" and "defendant," and religious references, with some extra keywords like "evidence" appearing as well.

    oai_token-act-pair · gemini-2.0-flash

    proof/evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Савезне
    -0.83
    BagConstraints
    -0.83
    rawDesc
    -0.80
    elemField
    -0.72
     oprot
    -0.71
    шње
    -0.69
     estimés
    -0.66
     _$
    -0.65
     termica
    -0.65
     كومونز
    -0.64
    POSITIVE LOGITS
     zelfs
    0.43
    Legături
    0.43
    でに
    0.43
     invari
    0.41
     face
    0.40
     even
    0.39
     int
    0.39
     past
    0.38
     most
    0.38
     déjà
    0.38
    Activations Density 3.894%

    No Known Activations