© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1886
    Prev
    Next
    INDEX
    Explanations

    code snippets, acronyms, and other technical terms

    oai_token-act-pair · gemini-2.0-flash

    sc

    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
     Sc
    -2.19
    Sc
    -2.11
     sc
    -2.11
    sc
    -1.99
     SC
    -1.83
    SC
    -1.59
     Sk
    -1.49
    Sk
    -1.42
     sk
    -1.38
     Scro
    -1.25
    POSITIVE LOGITS
     AssemblyTitle
    0.57
    +#+#
    0.56
     BorderRadius
    0.56
    ValueStyle
    0.55
    PositiveButton
    0.53
    原始内容存档于
    0.53
     betweenstory
    0.53
     Barton
    0.52
     LPC
    0.50
    Vorte
    0.49
    Activations Density 6.032%

    No Known Activations