© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13890
    Prev
    Next
    INDEX
    Explanations

    Arabic proper nouns, especially historical figures and place names.

    oai_token-act-pair · gemini-2.0-flash

    Arabic names and history

    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
     tslint
    -0.77
    uarts
    -0.70
     noqa
    -0.68
    luents
    -0.66
     pylint
    -0.62
    tacles
    -0.62
    (!__
    -0.61
    NUMX
    -0.60
     Normdatei
    -0.60
    sätzlich
    -0.59
    POSITIVE LOGITS
    ed
    0.49
    Manbalar
    0.49
    ib
    0.47
    em
    0.43
    if
    0.43
    im
    0.42
    XmlType
    0.41
    f
    0.40
    :✨
    0.40
    MessageTagHelper
    0.40
    Activations Density 0.669%

    No Known Activations