© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13480
    Prev
    Next
    INDEX
    Explanations

    snippets of French text surrounding Linux configuration and software issues, including words that contain accentuated characters and verbs in different tenses

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     remplacé
    -0.78
     interacted
    -0.73
     counted
    -0.73
     terminée
    -0.73
     thanked
    -0.73
     comforted
    -0.69
     healed
    -0.68
     danced
    -0.68
     contrasted
    -0.68
     redeemed
    -0.68
    POSITIVE LOGITS
    WebVitals
    0.66
     impregn
    0.60
    Was
    0.60
    rrggbb
    0.60
     ano
    0.59
     install
    0.59
     annot
    0.58
    prefixer
    0.58
    fillType
    0.58
     refurb
    0.57
    Activations Density 0.806%

    No Known Activations