© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9922
    Prev
    Next
    INDEX
    Explanations

    code snippets, file paths, and variable names, especially those related to "ngx" which likely refers to Nginx server configurations.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     متعلقه
    -1.05
    DeleteBehavior
    -0.87
    +#+#
    -0.86
    UnsafeEnabled
    -0.85
     *@
    -0.81
     cherchés
    -0.80
     noDo
    -0.80
    TypedDataSet
    -0.80
    LookAnd
    -0.79
     HasFactory
    -0.78
    POSITIVE LOGITS
    座
    0.49
     de
    0.45
     dos
    0.42
     something
    0.42
    <bos>
    0.41
    RS
    0.40
    ↵↵
    0.39
    Ex
    0.39
     montes
    0.38
    λαμβ
    0.38
    Activations Density 1.084%

    No Known Activations