© 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. 11378
    Prev
    Next
    INDEX
    Explanations

    family relationships in lists

    oai_token-act-pair · gemini-2.0-flash

    terms related to family and relationships

    np_token-act-pair-logits · gpt-4o-mini
    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
    PreExecute
    -0.59
    RefNanny
    -0.54
    avadoc
    -0.52
     rând
    -0.52
    PreAuthorize
    -0.48
    <bos>
    -0.47
    rawQuery
    -0.47
     picioare
    -0.46
    RegressionTest
    -0.46
    Its
    -0.46
    POSITIVE LOGITS
    出版年
    0.77
    SharedCtor
    0.73
    tagHelperRunner
    0.70
    enumi
    0.69
    providedIn
    0.64
    Hướng
    0.59
    ंदीखरीदारी
    0.58
     Wiktionnaire
    0.58
    ₂+
    0.58
     bezeichneter
    0.57
    Activations Density 0.886%

    No Known Activations