© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7277
    Prev
    Next
    INDEX
    Explanations

    terms relating to social issues, politics, and education, particularly when discussing challenges or improvements

    oai_token-act-pair · gemini-2.0-flash

    many

    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
    Negative Logits
    Mostly
    -0.68
     سكانية
    -0.66
    MOST
    -0.66
     Mostly
    -0.61
    RegistryLite
    -0.58
    most
    -0.56
    mostly
    -0.56
    ,:),
    -0.54
    OOTDTY
    -0.54
    Almost
    -0.53
    POSITIVE LOGITS
     many
    2.73
    many
    2.36
    Many
    2.20
     Many
    2.17
     MANY
    1.98
     muchos
    1.95
     muitos
    1.81
     muchas
    1.72
     molti
    1.71
     viele
    1.70
    Activations Density 7.697%

    No Known Activations