© 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. 751
    Prev
    Next
    INDEX
    Explanations

    tokens associated with citations, geographical regions, and the last names of people.

    oai_token-act-pair · 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
    httphttps
    -0.46
     Klicken
    -0.43
     gynhyrchwyd
    -0.42
    webElementXpaths
    -0.40
    monte
    -0.39
    rawDesc
    -0.39
    ]=-
    -0.39
     né
    -0.39
    InputGroup
    -0.38
    memoized
    -0.38
    POSITIVE LOGITS
     myſelf
    0.86
     itſelf
    0.85
     ſeveral
    0.85
     preſent
    0.80
     Chriftian
    0.76
     leſs
    0.74
     Efq
    0.73
     تانيه
    0.73
     faſt
    0.73
     laſt
    0.73
    Activations Density 1.238%

    No Known Activations