© 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. 6210
    Prev
    Next
    INDEX
    Explanations

    place names, locations, and other proper nouns

    oai_token-act-pair · gemini-2.0-flash

    terms related to Greek patients and medical contexts

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

    Locations

    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
     stället
    -0.60
    PRNewswire
    -0.58
    mergeFrom
    -0.58
     հղումներ
    -0.57
     externi
    -0.56
     Италијани
    -0.54
    новништво
    -0.54
     capitales
    -0.54
     Δη
    -0.53
    parsedMessage
    -0.53
    POSITIVE LOGITS
     дописавши
    0.56
    ểm
    0.52
    CloseOperation
    0.50
    mius
    0.49
     mergeFrom
    0.47
    KommentareTeilen
    0.47
    Diwedd
    0.47
    onomía
    0.46
     Moly
    0.46
    Throw
    0.45
    Activations Density 4.998%

    No Known Activations