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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11873
    Prev
    Next
    INDEX
    Explanations

    legal terminology and court decisions

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or keywords

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

    legal opinions

    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
    RectangleBorder
    -0.79
    parsedMessage
    -0.73
    tagHelperRunner
    -0.64
     الحره
    -0.57
     <=",
    -0.57
    іга
    -0.57
     externi
    -0.56
     تانيه
    -0.55
     مرئيه
    -0.55
    Демографія
    -0.52
    POSITIVE LOGITS
     unknownFields
    0.59
    findpost
    0.59
     postIndex
    0.57
    SpringRunner
    0.48
    UEL
    0.47
    colhead
    0.47
     noten
    0.47
    setopt
    0.47
    GeneratedValue
    0.46
    gdx
    0.46
    Activations Density 4.315%

    No Known Activations