© 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. 467
    Prev
    Next
    INDEX
    Explanations

    Chinese text related to sending messages

    oai_token-act-pair · gemini-2.0-flash

    字段Method: 1Reason: MAX_ACTIVATING_TOKENS mostly consist of non-English words.字段

    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
    OK
    -0.48
    J
    -0.45
    ano
    -0.44
    дж
    -0.44
    kr
    -0.44
    p
    -0.44
    k
    -0.43
    red
    -0.43
    ek
    -0.42
    j
    -0.42
    POSITIVE LOGITS
     مشين
    0.98
     AssemblyTitle
    0.75
     autorytatywna
    0.72
    RegistryLite
    0.71
    RectangleBorder
    0.69
    ruptedException
    0.68
    kloped
    0.66
     EconPapers
    0.63
     calendriers
    0.63
    Geplaatst
    0.62
    Activations Density 0.744%

    No Known Activations