© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3616
    Prev
    Next
    INDEX
    Explanations

    code and configuration snippets using the string "str" and "URI"

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uri
    -0.71
     uri
    -0.61
    URI
    -0.59
     URI
    -0.51
     Chambers
    -0.48
     Nile
    -0.48
    relle
    -0.47
    onete
    -0.45
    antemente
    -0.44
    osus
    -0.44
    POSITIVE LOGITS
    <bos>
    2.50
     itſelf
    0.74
    /*
    0.70
    Geplaatst
    0.67
     whoſe
    0.61
     faſt
    0.60
     raiſ
    0.60
     Monfieur
    0.59
     myſelf
    0.58
     Jefus
    0.58
    Activations Density 0.199%

    No Known Activations