© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    conspiratorial and politically charged language.

    oai_token-act-pair · gemini-2.0-flash

    programming or coding terminology

    np_token-act-pair-logits · gpt-4o-mini

    coding terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     edelstahl
    -0.54
    ()));
    -0.52
     générations
    -0.52
     "");
    -0.51
    seamnă
    -0.51
     dieux
    -0.50
     विश्वसनीयता
    -0.50
    )];
    -0.49
     Ternyata
    -0.47
     courants
    -0.45
    POSITIVE LOGITS
     BoxFit
    0.74
    qtype
    0.69
     sort
    0.69
     BoxDecoration
    0.67
     type
    0.66
    offsetof
    0.64
    IsContent
    0.62
    IUrlHelper
    0.58
     Sort
    0.58
     kind
    0.58
    Activations Density 15.062%

    No Known Activations