© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10307
    Prev
    Next
    INDEX
    Explanations

    strings of words in Romance languages related to asking for help understanding code

    oai_token-act-pair · gemini-2.0-flash

    code and chat snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     aikaa
    -0.21
     verksamhet
    -0.21
     händer
    -0.20
     teratur
    -0.19
     bordados
    -0.19
     igång
    -0.18
     mukana
    -0.17
     löyty
    -0.17
     ánimo
    -0.17
     långt
    -0.17
    POSITIVE LOGITS
    <bos>
    0.83
     houſe
    0.73
     Inscrivez
    0.71
     CHAPITRE
    0.69
     Anſ
    0.68
    ſelf
    0.66
     NDEBUG
    0.66
     myſelf
    0.66
     pleaſure
    0.66
     Diſ
    0.65
    Activations Density 3.680%

    No Known Activations