© 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. 3666
    Prev
    Next
    INDEX
    Explanations

    the word "told" near commas and other words/articles

    oai_token-act-pair · gemini-2.0-flash

    told

    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
    complexType
    -0.55
    бор
    -0.53
    StoryboardSegue
    -0.53
    strick
    -0.52
    alış
    -0.51
    =$(
    -0.48
    kháu
    -0.47
     Lightfoot
    -0.47
     filter
    -0.47
    minas
    -0.47
    POSITIVE LOGITS
    RegressionTest
    0.78
    SharedDtor
    0.67
     >=",
    0.63
     gawas
    0.59
    Trayectoria
    0.56
    ]--;
    0.56
    )$/,
    0.55
     surla
    0.54
     Мексичка
    0.54
    CloseOperation
    0.53
    Activations Density 1.157%

    No Known Activations