© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    words related to actions and making decisions or judgements.

    oai_token-act-pair · gemini-2.0-flash

    the concept of "above"

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

    above

    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
    __);
    -0.58
    cionario
    -0.47
    makeConstraints
    -0.46
    )";
    -0.44
     comuniques
    -0.44
    lanmış
    -0.43
    atonic
    -0.43
    لينكات
    -0.43
    TryGetValue
    -0.43
     برانيه
    -0.42
    POSITIVE LOGITS
     above
    3.44
    above
    3.19
     Above
    3.08
    Above
    3.05
     ABOVE
    2.70
     acima
    2.39
    ABOVE
    2.19
    bove
    1.88
     diatas
    1.82
     below
    1.70
    Activations Density 1.451%

    No Known Activations