© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1526
    Prev
    Next
    INDEX
    Explanations

    code and programming related terms especially from C and Ruby

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    KURZBESCHREIBUNG
    -0.50
    </strong>
    -0.42
    </b>
    -0.41
    ADELPHIA
    -0.41
    dropIfExists
    -0.40
    ...
    -0.40
     stad
    -0.39
    File
    -0.39
     cul
    -0.38
     ahu
    -0.38
    POSITIVE LOGITS
    Autoritní
    0.98
    ]--;
    0.86
    TestingModule
    0.80
    AccessorTable
    0.79
    SharedDtor
    0.77
    InjectAttribute
    0.75
    webElement
    0.75
    RegistryLite
    0.74
    __":
    0.72
    Vidite
    0.72
    Activations Density 7.400%

    No Known Activations