© 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. 428
    Prev
    Next
    INDEX
    Explanations

    code and xml markup with some math symbols mixed in

    oai_token-act-pair · gemini-2.0-flash

    Android 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
     vuitton
    -0.63
    AutoScale
    -0.60
    strptime
    -0.59
    TryParse
    -0.58
    awtextra
    -0.57
    Jegyzetek
    -0.56
    useEffect
    -0.55
     wors
    -0.54
     الرياضيه
    -0.54
    Referanser
    -0.53
    POSITIVE LOGITS
    RegistryLite
    0.62
    Tikang
    0.58
    ItemBackground
    0.54
    Datuak
    0.53
    MigrationBuilder
    0.52
    สือ
    0.51
    يكب
    0.51
    Gweler
    0.50
    <?>>
    0.49
    smithy
    0.48
    Activations Density 5.040%

    No Known Activations