© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13278
    Prev
    Next
    INDEX
    Explanations

    regular expressions and file paths in code

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -1.63
    expandindo
    -1.21
    RenderAtEndOf
    -1.16
     betweenstory
    -1.13
     Савезне
    -1.10
     виправивши
    -1.09
     Италијани
    -1.05
    AsUp
    -1.05
    IUrlHelper
    -1.05
    PerformLayout
    -1.03
    POSITIVE LOGITS
     (
    0.49
    ,
    0.49
     ,
    0.45
    .
    0.44
     c
    0.44
    ;
    0.44
     po
    0.43
     up
    0.42
     i
    0.41
    :
    0.41
    Activations Density 5.770%

    No Known Activations