© 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. 7209
    Prev
    Next
    INDEX
    Explanations

    the word "direct" and words associated with evidence or direction

    oai_token-act-pair · gemini-2.0-flash

    direct

    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
     direct
    -3.20
    Direct
    -3.20
    direct
    -3.17
     Direct
    -3.16
     directly
    -2.86
     Directly
    -2.77
     DIRECT
    -2.75
    directly
    -2.75
    DIRECT
    -2.64
     directe
    -2.63
    POSITIVE LOGITS
    TagHelper
    0.50
    참고
    0.50
    ẫu
    0.49
    fer
    0.47
    edith
    0.42
    ін
    0.42
     asemenea
    0.40
    belongsTo
    0.40
    lim
    0.39
    instein
    0.39
    Activations Density 1.888%

    No Known Activations