© 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. 9751
    Prev
    Next
    INDEX
    Explanations

    legal text, identifying key points of argumentation or analysis.

    oai_token-act-pair · gemini-2.0-flash

    function words

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

    This/That

    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
    AccessorTable
    -0.42
    گران
    -0.40
    RegressionTest
    -0.39
    und
    -0.38
    iotensin
    -0.38
     true
    -0.37
    Демографія
    -0.35
     True
    -0.35
     jem
    -0.35
    Bibliograf
    -0.35
    POSITIVE LOGITS
     is
    0.77
    帖最后由
    0.77
    TemporalType
    0.71
     raises
    0.69
    subpackage
    0.68
    %");
    0.68
     echoes
    0.68
     points
    0.68
    bibfield
    0.67
     iſt
    0.65
    Activations Density 2.085%

    No Known Activations