© 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. 16046
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and places, especially in the context of news or information

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    <bos>
    -0.85
    IContainer
    -0.66
    memoized
    -0.65
    GEBURTS
    -0.60
     Roskov
    -0.57
    はじめに
    -0.57
     @"/
    -0.56
     Италијани
    -0.56
     
    -0.55
    testcase
    -0.54
    POSITIVE LOGITS
     myſelf
    0.89
     iſt
    0.77
    ^(@)
    0.77
     purpoſe
    0.77
     ſeveral
    0.73
     whoſe
    0.72
     Majefty
    0.72
     ſhe
    0.71
     doubtnut
    0.71
     preſent
    0.69
    Activations Density 4.613%

    No Known Activations