© 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. 9755
    Prev
    Next
    INDEX
    Explanations

    angle brackets followed by text, which is common notation for HTML/XML.

    oai_token-act-pair · gemini-2.0-flash

    HTML forms

    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
     forms
    -3.00
     form
    -2.97
     Forms
    -2.67
     Form
    -2.52
    forms
    -2.47
     FORMS
    -2.47
    form
    -2.44
    Forms
    -2.41
    Form
    -2.31
     FORM
    -2.20
    POSITIVE LOGITS
    InSection
    0.60
    interopRequire
    0.49
     inci
    0.47
    raph
    0.46
    JNIEnv
    0.46
     متعلقه
    0.46
    circum
    0.45
    ıza
    0.44
    графия
    0.43
    nextProps
    0.43
    Activations Density 0.570%

    No Known Activations