© 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. 9246
    Prev
    Next
    INDEX
    Explanations

    language related to government finance

    oai_token-act-pair · gemini-2.0-flash

    terms related to borrowing or debt

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

    debt

    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
    tidine
    -0.39
     culturelles
    -0.39
    jeni
    -0.38
    ika
    -0.37
     ModelExpression
    -0.37
    letto
    -0.36
    roup
    -0.36
    Divider
    -0.36
     गणना
    -0.36
    根
    -0.36
    POSITIVE LOGITS
     borrow
    0.98
     borrowed
    0.81
     borrowing
    0.79
    borrow
    0.79
    InjectAttribute
    0.75
     utafitiHapana
    0.75
    adpleegd
    0.75
    ANTLR
    0.74
    bonded
    0.74
    mybatisplus
    0.73
    Activations Density 1.813%

    No Known Activations