© 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. 10895
    Prev
    Next
    INDEX
    Explanations

    text referring to trains and railroads, including trails and train safety measures

    oai_token-act-pair · gemini-2.0-flash

    railroads

    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
    RectangleBorder
    -0.85
    UnsafeEnabled
    -0.71
    XmlType
    -0.69
    KommentareTeilen
    -0.63
     carriage
    -0.61
    LookAnd
    -0.60
    SizeF
    -0.56
    ExtendWith
    -0.56
     carriages
    -0.56
    LLocation
    -0.55
    POSITIVE LOGITS
     units
    0.55
     Rutland
    0.53
     swit
    0.49
     Talley
    0.49
     switching
    0.48
    arzt
    0.48
    switching
    0.48
     Units
    0.47
    witcher
    0.47
     snippetHide
    0.47
    Activations Density 1.952%

    No Known Activations