© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10238
    Prev
    Next
    INDEX
    Explanations

    various elements of computer code, especially related to API requests and data structures.

    oai_token-act-pair · gemini-2.0-flash

    Code segments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     itſelf
    -1.68
     myſelf
    -1.65
     themſelves
    -1.55
    ſelf
    -1.52
     Jefus
    -1.51
    ſelves
    -1.48
     Efq
    -1.48
    ^(@)
    -1.48
     pleaſure
    -1.45
     Majefty
    -1.45
    POSITIVE LOGITS
    ↵↵
    0.73
     
    0.70
    ↵
    0.65
    <eos>
    0.64
    ,
    0.62
    .
    0.61
     (
    0.59
    /
    0.59
     p
    0.58
     pa
    0.56
    Activations Density 1.415%

    No Known Activations