© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14181
    Prev
    Next
    INDEX
    Explanations

    biographical details about people

    oai_token-act-pair · gemini-2.0-flash

    people's bios

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     houſe
    -0.54
     ſeveral
    -0.53
    **/
    -0.48
     Theſe
    -0.48
    DispatchToProps
    -0.47
    WebVitals
    -0.47
    UnknownFields
    -0.47
     Anſ
    -0.46
     himſelf
    -0.46
     neceffary
    -0.46
    POSITIVE LOGITS
     nakalista
    0.79
    +#+#
    0.63
    CurrentValue
    0.63
    ագրություններ
    0.59
    addPreferredGap
    0.59
     незавершена
    0.59
     ویکی‌آمباردا
    0.58
    ConstraintMaker
    0.57
     تضيفلها
    0.56
     utafitiHapana
    0.56
    Activations Density 1.325%

    No Known Activations