© 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. 5697
    Prev
    Next
    INDEX
    Explanations

    the word "Nor" or "Sou" indicating a place or person from Norway or the Southern United States

    oai_token-act-pair · gemini-2.0-flash

    technical terms or identifiers related to programming or software development

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

    Nor

    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
    PropertyChanging
    -0.53
    DockStyle
    -0.52
    דת
    -0.48
    surate
    -0.48
     sym
    -0.48
    ngrx
    -0.47
    IsContent
    -0.47
    prettier
    -0.47
    存于互联网档案馆
    -0.46
    PreAuthorize
    -0.45
    POSITIVE LOGITS
     HasFactory
    0.64
     resourceCulture
    0.64
    MigrationBuilder
    0.63
    ंदीखरीदारी
    0.62
     nahilalakip
    0.60
    getchar
    0.59
    writeFieldEnd
    0.56
    FieldDescriptor
    0.54
     BorderRadius
    0.53
    ValueStyle
    0.52
    Activations Density 0.197%

    No Known Activations