© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12463
    Prev
    Next
    INDEX
    Explanations

    code snippets or structured data with nested brackets and quotes, potentially key-value pairs

    oai_token-act-pair · gemini-2.0-flash

    closing brackets

    np_max-act · 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
    Negative Logits
     дописавши
    -0.54
     IANS
    -0.50
    Портал
    -0.47
    綜合報導
    -0.47
     sauce
    -0.45
    原始内容存档于
    -0.45
     SwitchCompat
    -0.44
    ніципалі
    -0.44
     façons
    -0.43
    Sauce
    -0.42
    POSITIVE LOGITS
    AndroidJUnit
    0.63
    VersionUID
    0.60
    randomUUID
    0.57
    AddHtmlAttribute
    0.55
     purpoſe
    0.54
    ugt
    0.54
     tartalomajánló
    0.54
    spt
    0.52
     DriverManager
    0.52
     faſt
    0.51
    Activations Density 2.598%

    No Known Activations