© 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. 11113
    Prev
    Next
    INDEX
    Explanations

    text describing membership in religious organizations and locations of residence

    oai_token-act-pair · gemini-2.0-flash

    Biographical information

    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
     незавершена
    -0.61
    OGND
    -0.61
     Omen
    -0.56
     Stimme
    -0.56
    ufen
    -0.55
    __*/
    -0.53
    iches
    -0.52
    parsedMessage
    -0.51
    AndEndTag
    -0.50
    BindView
    -0.50
    POSITIVE LOGITS
    RectangleBorder
    0.68
     FontWeight
    0.61
    #+#
    0.56
     saites
    0.56
    rofoam
    0.54
    <?,
    0.50
    ctez
    0.50
    mybatisplus
    0.50
    étro
    0.48
    ptonshire
    0.47
    Activations Density 0.465%

    No Known Activations