© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12942
    Prev
    Next
    INDEX
    Explanations

    regular expressions for URL parsing, file redirection, or text matching

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     насељу
    -0.73
    FormTagHelper
    -0.64
     незавершена
    -0.62
    AutoField
    -0.59
    DispatchToProps
    -0.59
    "}")
    -0.59
    setVerticalGroup
    -0.58
    FunctionFlags
    -0.57
    dehyde
    -0.57
    ^(@)
    -0.57
    POSITIVE LOGITS
     تضيفلها
    0.56
     SwitchCompat
    0.44
     ganzes
    0.43
    InSection
    0.42
     patty
    0.40
    ConstraintMaker
    0.40
    getResource
    0.40
    |$
    0.39
     getChild
    0.39
    initWithFrame
    0.38
    Activations Density 4.408%

    No Known Activations