© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2318
    Prev
    Next
    INDEX
    Explanations

    instances of research being done

    oai_token-act-pair · gemini-2.0-flash

    research-related actions

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

    Experiments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.60
    PhysRevLett
    -0.56
    Gweler
    -0.53
    SqlParameter
    -0.52
    IUrlHelper
    -0.47
     reunió
    -0.47
    
    -0.47
     ofreció
    -0.46
    rather
    -0.46
    程度上
    -0.46
    POSITIVE LOGITS
     carried
    0.78
     performed
    0.74
     conducted
    0.69
     undertaken
    0.67
     GIPHY
    0.62
    Carry
    0.60
    ništvo
    0.59
    migrationBuilder
    0.58
     initiated
    0.57
     houſe
    0.57
    Activations Density 1.630%

    No Known Activations