© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8921
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "to" in different contexts, some of which involve obligation or purpose

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Diweddarwch
    -0.75
     kasarigan
    -0.74
     thôi
    -0.63
     للمعارف
    -0.59
     Unto
    -0.57
    èdia
    -0.56
    مراجع
    -0.54
    ائص
    -0.52
    ❹
    -0.51
    RTEX
    -0.51
    POSITIVE LOGITS
    IBOutlet
    0.61
    Viited
    0.57
    NameInMap
    0.53
     насеље
    0.53
    __":
    0.53
     IBOutlet
    0.52
     defaultstate
    0.50
     métier
    0.50
     كومونز
    0.50
    __':
    0.49
    Activations Density 0.978%

    No Known Activations