© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    code snippets related to JSON parsing in C#

    oai_token-act-pair · gemini-2.0-flash

    Program file operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MLA
    -0.53
    ngdoc
    -0.52
    attan
    -0.52
     Squ
    -0.51
     nuage
    -0.50
    ugt
    -0.50
     vets
    -0.49
    Spoljašnje
    -0.48
     Haig
    -0.48
     Participants
    -0.47
    POSITIVE LOGITS
    FileDescriptor
    0.66
     fread
    0.64
    InitStruct
    0.63
    XmlEnum
    0.62
     resourceCulture
    0.55
    fptr
    0.55
    feof
    0.55
    HasForeignKey
    0.55
    featureID
    0.54
    fwrite
    0.54
    Activations Density 16.491%

    No Known Activations