© 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. 715
    Prev
    Next
    INDEX
    Explanations

    lines of code, especially those involving jQuery selectors, variable assignment, and URL encoding, and also the word Conservation

    oai_token-act-pair · gemini-2.0-flash

    ")

    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
    ")
    -1.37
    ')
    -1.33
    ")))
    -1.19
    ").
    -1.18
    ').
    -1.17
    '))
    -1.16
    ')))
    -1.16
    '):
    -1.16
    "):
    -1.15
    ']
    -1.13
    POSITIVE LOGITS
     PWN
    0.60
    Expedia
    0.60
     Hauteur
    0.59
    AnchorStyles
    0.59
     Anſ
    0.58
     MIPS
    0.57
    Javadoc
    0.57
    ViewInit
    0.56
     greateſt
    0.56
    出版年
    0.56
    Activations Density 6.582%

    No Known Activations