© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 548
    Prev
    Next
    INDEX
    Explanations

    dates and location prepositions within a historical context

    oai_token-act-pair · gemini-2.0-flash

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '\\;'
    -0.73
     تضيفلها
    -0.69
    ValueStyle
    -0.68
    MigrationBuilder
    -0.65
    UrlResolution
    -0.62
     ExecuteAsync
    -0.60
    ंदीखरीदारी
    -0.59
    IsMutable
    -0.57
     nakalista
    -0.54
     kasarigan
    -0.53
    POSITIVE LOGITS
    Phan
    0.33
    Orsay
    0.32
    INION
    0.31
    Hasan
    0.31
    Dang
    0.30
    Thy
    0.30
    čník
    0.29
    Ĭ
    0.29
    Eck
    0.29
    Į
    0.29
    Activations Density 2.488%

    No Known Activations