© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10693
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" preceded by a verb indicating intent or action

    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
    ValueStyle
    -0.86
     يتيمه
    -0.75
    Geplaatst
    -0.68
    apimachinery
    -0.66
    niająca
    -0.65
     JpaRepository
    -0.64
     MotionEvent
    -0.60
     متعلقه
    -0.58
     كومونز
    -0.57
     ProtoMessage
    -0.57
    POSITIVE LOGITS
     learn
    0.67
     learning
    0.61
     learned
    0.52
     aprender
    0.51
     learns
    0.51
     imparare
    0.49
     Learn
    0.48
     aprendizagem
    0.47
     dig
    0.47
    learning
    0.47
    Activations Density 2.264%

    No Known Activations