© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13864
    Prev
    Next
    INDEX
    Explanations

    time-critical business news

    oai_token-act-pair · gemini-2.0-flash

    update

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     kasarigan
    -0.75
    ArrowToggle
    -0.63
     otomatig
    -0.62
     muualla
    -0.58
    enterOuterAlt
    -0.58
     Réponses
    -0.56
    tagHelperRunner
    -0.55
    LayoutStyle
    -0.54
    usermodel
    -0.49
    inete
    -0.49
    POSITIVE LOGITS
     update
    2.77
     updates
    2.59
     Update
    2.48
    update
    2.36
    Update
    2.31
     Updates
    2.30
     updating
    2.23
     UPDATE
    2.11
    Updates
    2.11
    updates
    2.08
    Activations Density 0.802%

    No Known Activations