© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1282
    Prev
    Next
    INDEX
    Explanations

    mixed Chinese and English programming-related text

    oai_token-act-pair · gemini-2.0-flash

    开

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RUnlock
    -0.58
    QtWidgets
    -0.55
    createServer
    -0.53
    öy
    -0.53
    ftagPool
    -0.52
     QtCore
    -0.50
    fillType
    -0.49
     up
    -0.48
    setCancelable
    -0.47
    RTLR
    -0.47
    POSITIVE LOGITS
    了下来
    0.88
    了下去
    0.84
    起来了
    0.78
    了出去
    0.74
    了出来
    0.70
    出来了
    0.70
    了起来
    0.69
    着了
    0.69
     surla
    0.68
    了过去
    0.65
    Activations Density 0.103%

    No Known Activations