© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 553
    Prev
    Next
    INDEX
    Explanations

    seemingly random letters in a legal document

    oai_token-act-pair · gemini-2.0-flash

    Legal documents, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    writeField
    -0.69
    SPJ
    -0.65
    ActionMode
    -0.64
    IsContent
    -0.64
     Ety
    -0.63
     allAfrica
    -0.61
    xaml
    -0.60
     ANI
    -0.59
    CopyWith
    -0.59
     CIL
    -0.58
    POSITIVE LOGITS
    BURGH
    0.44
     ExecuteAsync
    0.43
    ControllerTest
    0.38
     oprot
    0.38
     виправивши
    0.37
    leyebilirsiniz
    0.36
     definiti
    0.36
     đặc
    0.36
    nextDouble
    0.35
    softc
    0.35
    Activations Density 1.090%

    No Known Activations