© 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. 1187
    Prev
    Next
    INDEX
    Explanations

    German words and abbreviations, especially those related to a specific library or university in Saarbrucken.

    oai_token-act-pair · gemini-2.0-flash

    German and mathematical texts

    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
    ValueStyle
    -0.72
    Portale
    -0.66
     autorytatywna
    -0.65
    RegistryLite
    -0.61
    quelize
    -0.58
    Дереккөздер
    -0.58
    parsedMessage
    -0.56
     TextInputType
    -0.54
    InstrumentedTest
    -0.54
    uxxxx
    -0.54
    POSITIVE LOGITS
    lany
    0.53
    usis
    0.50
    mopol
    0.49
    inheritDoc
    0.49
    nass
    0.48
    eclampsia
    0.48
    tingly
    0.48
    lyl
    0.47
    lyk
    0.47
    هات
    0.47
    Activations Density 0.489%

    No Known Activations