© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 319
    Prev
    Next
    INDEX
    Explanations

    uses of the word "to"

    oai_token-act-pair · gemini-2.0-flash

    Long, argumentative sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    awtextra
    -0.93
    yntaxException
    -0.70
    </thead>
    -0.65
    setVerticalGroup
    -0.64
    ỡng
    -0.64
    InjectAttribute
    -0.63
     CreateTagHelper
    -0.61
    ModelAdmin
    -0.60
    Hozzáférés
    -0.60
    rostis
    -0.60
    POSITIVE LOGITS
    Collegamenti
    0.58
     Voraus
    0.50
     lernen
    0.49
    inerea
    0.47
    newArrayList
    0.46
     cryptic
    0.46
    <?>>
    0.45
     Bask
    0.45
     destacan
    0.45
    żer
    0.45
    Activations Density 5.006%

    No Known Activations