© 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. 11653
    Prev
    Next
    INDEX
    Explanations

    words related to announcements and leaving

    oai_token-act-pair · gemini-2.0-flash

    Business news

    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
     Marks
    -0.48
    Marker
    -0.47
     thao
    -0.46
    Markers
    -0.46
    Marks
    -0.45
     Censo
    -0.45
    WebDriver
    -0.44
    beforeAll
    -0.44
     Grass
    -0.43
     vettor
    -0.43
    POSITIVE LOGITS
    EndProject
    0.68
    kháu
    0.68
     Мексичка
    0.66
     AspNetCore
    0.65
     surla
    0.64
    RuleContext
    0.63
    XtraGrid
    0.63
    BagConstraints
    0.61
     comes
    0.60
    anuts
    0.60
    Activations Density 2.051%

    No Known Activations