© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14173
    Prev
    Next
    INDEX
    Explanations

    a wide array of words, often acronyms, abbreviations, and words associated with legal or technical jargon.

    oai_token-act-pair · gemini-2.0-flash

    code/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     صوتيه
    -0.73
    enumi
    -0.57
     néglig
    -0.55
    日閲覧
    -0.53
    Enllaces
    -0.53
    🧵
    -0.52
    ChildScrollView
    -0.52
     AssemblyCulture
    -0.52
    RectangleBorder
    -0.52
    OGND
    -0.51
    POSITIVE LOGITS
     betweenstory
    0.58
    SpringBootTest
    0.57
    mitian
    0.55
     BrowserModule
    0.54
     ddelweddau
    0.53
    })`
    0.48
    nhi
    0.48
    SceneManagement
    0.47
    ditionally
    0.47
    ixe
    0.46
    Activations Density 14.218%

    No Known Activations