© 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. 507
    Prev
    Next
    INDEX
    Explanations

    the word "full", often in association with hyphens and other words that indicate quantity or duration.

    oai_token-act-pair · gemini-2.0-flash

    full positions

    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
     full
    -0.96
     Full
    -0.91
    Full
    -0.90
     FULL
    -0.81
    full
    -0.80
    FULL
    -0.72
     penuh
    -0.65
     Voll
    -0.63
     fully
    -0.61
     peł
    -0.60
    POSITIVE LOGITS
     autorytatywna
    0.88
    NameInMap
    0.80
    OGND
    0.70
    URLException
    0.68
    PreferredItem
    0.65
    Tikang
    0.65
    MigrationBuilder
    0.65
     للاسماء
    0.64
     referenties
    0.64
     '\\;'
    0.63
    Activations Density 1.768%

    No Known Activations