© 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. 15173
    Prev
    Next
    INDEX
    Explanations

    instances where "to" is used as an infinitive marker, signaling an action or purpose, along with auxiliary verbs and hedging language.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    )";
    -0.67
    تقاوى
    -0.63
    "]();
    -0.62
    !")
    -0.60
    ")));
    -0.60
     XCTest
    -0.59
    ]=>
    -0.59
    atguigu
    -0.58
    AutoField
    -0.57
    "):
    -0.57
    POSITIVE LOGITS
    urgy
    0.46
     stie
    0.45
    FetchType
    0.45
    AccessFile
    0.44
     Hit
    0.42
    TextAppearance
    0.42
     épaules
    0.42
    estrian
    0.41
     burn
    0.41
    äfte
    0.41
    Activations Density 1.175%

    No Known Activations