© 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. 11989
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    computer code and errors

    np_max-act-logits · gemini-2.0-flash

    say "space function words"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     dataSnapshot
    -0.66
     EconPapers
    -0.66
    TypedDataSet
    -0.63
    ConstraintMaker
    -0.61
    BindingResult
    -0.57
    WebVitals
    -0.56
    RectangleBorder
    -0.55
    SpringRunner
    -0.55
     nakalista
    -0.54
     дописавши
    -0.53
    POSITIVE LOGITS
     {}));
    0.61
    RepeatedField
    0.56
     Them
    0.54
     AssemblyCulture
    0.50
    argli
    0.48
     Ignoring
    0.46
     fitting
    0.46
    Them
    0.45
     Lung
    0.45
     JAXB
    0.45
    Activations Density 0.560%

    No Known Activations