© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3736
    Prev
    Next
    INDEX
    Explanations

    legal language and statutory references

    oai_token-act-pair · gemini-2.0-flash

    words or phrases related to legal documents and definitions

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

    Legal codes

    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
    ();)
    -0.52
    łaj
    -0.47
    esterday
    -0.47
    ември
    -0.45
    (;;)
    -0.44
    ondale
    -0.43
    $<$
    -0.42
    ándote
    -0.42
    migrationBuilder
    -0.42
    `.`
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.79
     gynhyrchwyd
    0.73
    OGND
    0.71
     Wikimedijinoj
    0.68
     Paglinawan
    0.67
    RegistryLite
    0.67
    HtmlAttribute
    0.67
    帖最后由
    0.66
     beginnetje
    0.66
    BeginContext
    0.65
    Activations Density 3.634%

    No Known Activations