© 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. 9236
    Prev
    Next
    INDEX
    Explanations

    text describing predictive distributions in neural networks

    oai_token-act-pair · gemini-2.0-flash

    technical terminology related to data analysis

    np_token-act-pair-logits · gpt-4o-mini
    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
    ChildScrollView
    -0.59
     Reverso
    -0.54
     Puebla
    -0.48
     chỉnh
    -0.48
    <?,
    -0.47
    Fractal
    -0.47
    ("]");
    -0.46
     ujednoznacz
    -0.46
    uegos
    -0.46
     siento
    -0.46
    POSITIVE LOGITS
     getItemId
    0.66
     ground
    0.63
    enumi
    0.58
    devise
    0.58
    awtextra
    0.58
    AILABILITY
    0.56
     Ground
    0.55
     שוליים
    0.54
     "..\..\..\
    0.54
    featureID
    0.54
    Activations Density 2.865%

    No Known Activations