© 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. 14231
    Prev
    Next
    INDEX
    Explanations

    code and technical writing, especially related to locating views or objects in a structured system.

    oai_token-act-pair · gemini-2.0-flash

    Code/technical documentation

    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
    tagHelperRunner
    -0.84
     surla
    -0.58
    ignano
    -0.58
    MergeFrom
    -0.54
     juger
    -0.52
     vertes
    -0.50
     něko
    -0.50
     humains
    -0.49
     gyakor
    -0.49
     protoimpl
    -0.49
    POSITIVE LOGITS
    Sucesor
    0.69
    reys
    0.65
     propOrder
    0.59
    prepareStatement
    0.56
    awtextra
    0.55
     kaarangay
    0.54
    NameValuePair
    0.53
    XmlType
    0.53
    SourceChecksum
    0.51
    TypedDataSet
    0.50
    Activations Density 5.153%

    No Known Activations