© 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. 9355
    Prev
    Next
    INDEX
    Explanations

    text related to quantifying medical risk and probability

    oai_token-act-pair · gemini-2.0-flash

    forms of the word 'develop'

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

    develop

    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
    _
    -0.93
     _
    -0.73
    \_
    -0.68
     cause
    -0.48
    theim
    -0.47
    VersionUID
    -0.47
     الحره
    -0.45
    getElementById
    -0.44
     افت
    -0.44
    Bree
    -0.44
    POSITIVE LOGITS
     develops
    1.53
     develop
    1.44
     developed
    1.32
     developing
    1.29
     Develop
    1.24
    developing
    1.24
     Developing
    1.20
    develop
    1.20
     Developed
    1.16
    Developing
    1.16
    Activations Density 2.974%

    No Known Activations