© 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. 4376
    Prev
    Next
    INDEX
    Explanations

    phrases such as "or", "to", "from" and "need" that connect ideas or elements in a list or process.

    oai_token-act-pair · gemini-2.0-flash

    numeric indicators or quantities

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

    numbers

    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
    sigkeit
    -0.52
    ⓧ
    -0.47
    addPreferredGap
    -0.46
    addGap
    -0.46
    nością
    -0.44
    SequentialGroup
    -0.44
    PhysRevD
    -0.42
    ẫ
    -0.42
    anthes
    -0.40
    <tfoot>
    -0.40
    POSITIVE LOGITS
     two
    2.61
     three
    2.53
     four
    2.41
    two
    2.31
    three
    2.20
     deux
    2.09
     five
    2.08
    four
    2.03
     trois
    2.00
     THREE
    1.98
    Activations Density 4.128%

    No Known Activations