© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7672
    Prev
    Next
    INDEX
    Explanations

    words related to reading and publishing like books, readers, companies, and publication

    oai_token-act-pair · gemini-2.0-flash

    reader

    np_max-act · gemini-2.0-flash

    reader

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Demografía
    -0.93
     referenties
    -0.93
    olesale
    -0.87
    bibinfo
    -0.86
    bibfield
    -0.84
    الإنجليزية
    -0.82
     IBRARY
    -0.82
     تانيه
    -0.81
     myſelf
    -0.80
    Folgende
    -0.80
    POSITIVE LOGITS
    (
    0.50
    )
    0.47
    `
    0.45
    某
    0.45
    I
    0.45
    "
    0.45
    \
    0.43
    is
    0.43
    '
    0.43
    us
    0.42
    Activations Density 1.840%

    No Known Activations