© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14518
    Prev
    Next
    INDEX
    Explanations

    proper nouns and code-related terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    endmodule
    -0.50
     betweenstory
    -0.48
    cshtml
    -0.47
    KURZBESCHREIBUNG
    -0.47
     protoimpl
    -0.40
     ویکی‌پدیا
    -0.39
    DIPSETTING
    -0.39
    AutoScale
    -0.39
    iesen
    -0.39
    copal
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.85
     informée
    0.62
    isNameExpr
    0.60
    Autoritní
    0.59
    łaszcza
    0.59
    alagi
    0.59
     AssemblyTitle
    0.58
     المعيارى
    0.57
    Uninitialized
    0.57
     հղումներ
    0.57
    Activations Density 9.734%

    No Known Activations