© 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. 10709
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "by" and the concept of an alias or pseudonym.

    oai_token-act-pair · gemini-2.0-flash

    Aliases and legal text

    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
     Italijani
    -0.66
     contextLoads
    -0.65
    期刊论文
    -0.65
     purpoſe
    -0.61
     againſt
    -0.61
     becauſe
    -0.60
     quæ
    -0.59
    ArgumentParser
    -0.57
    Portály
    -0.56
     houſe
    -0.56
    POSITIVE LOGITS
     alias
    0.83
     name
    0.82
     initComponents
    0.81
     aliases
    0.79
    <bos>
    0.75
     names
    0.68
    name
    0.67
     Name
    0.67
     moniker
    0.65
     nickname
    0.63
    Activations Density 0.729%

    No Known Activations