© 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. 12738
    Prev
    Next
    INDEX
    Explanations

    words that are relevant to politics, health, government, injuries, and elections.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and jargon

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

    Formal or legal text

    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
    com
    -0.49
    eman
    -0.48
    den
    -0.47
    of
    -0.47
    lad
    -0.47
    ful
    -0.46
    dan
    -0.46
    san
    -0.45
    ann
    -0.45
    dir
    -0.45
    POSITIVE LOGITS
    abestanden
    0.88
     AttributeSet
    0.85
     kasarigan
    0.85
     ModelExpression
    0.84
    setVerticalGroup
    0.84
    Билгалдахарш
    0.81
    MemoryWarning
    0.79
     nahilalakip
    0.78
    তথ্যসূত্র
    0.77
    ContentAsync
    0.75
    Activations Density 10.482%

    No Known Activations