© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12901
    Prev
    Next
    INDEX
    Explanations

    a mix of programming syntax, mathematical quantifications, medical terminology, and date-related terms, suggesting it is identifying technical or scientific language.

    oai_token-act-pair · gemini-2.0-flash

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    AndEndTag
    -0.62
     esternos
    -0.54
    GenerationType
    -0.54
    AndroidJUnit
    -0.53
    Enlaces
    -0.53
    InputBorder
    -0.51
    DockStyle
    -0.50
    InstrumentedTest
    -0.48
    Спасылкі
    -0.46
    laterra
    -0.43
    POSITIVE LOGITS
    ètres
    0.56
    Geplaatst
    0.54
    EndGlobalSection
    0.53
    ']);
    0.53
     }}"></
    0.52
    imap
    0.50
    }}$\\
    0.50
    onor
    0.50
    >");
    0.50
    UnsafeEnabled
    0.49
    Activations Density 8.142%

    No Known Activations