© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5539
    Prev
    Next
    INDEX
    Explanations

    the prepositions: of, to, for, and in

    oai_token-act-pair · gemini-2.0-flash

    the phrase 'way of'

    np_token-act-pair-logits · gpt-4o-mini

    "way of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ways
    -0.92
     Ways
    -0.81
     way
    -0.81
     WAYS
    -0.77
     resourceCulture
    -0.77
    Ways
    -0.76
    SourceChecksum
    -0.71
    Way
    -0.70
    way
    -0.69
     moyens
    -0.69
    POSITIVE LOGITS
    존
    0.57
    ARES
    0.53
    Rhestr
    0.50
    olson
    0.49
    Processing
    0.48
     tana
    0.48
    Elmer
    0.47
     processing
    0.47
    chkin
    0.47
     existence
    0.47
    Activations Density 1.058%

    No Known Activations