© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12320
    Prev
    Next
    INDEX
    Explanations

    words in languages other than English, especially French and Portuguese, and also some programming terms

    oai_token-act-pair · gemini-2.0-flash

    non-English

    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
    ]--;
    -0.54
    atisch
    -0.47
    hanno
    -0.47
    gonic
    -0.45
    mits
    -0.44
    multipart
    -0.44
     Uns
    -0.43
    INFL
    -0.43
     Around
    -0.42
    orescent
    -0.42
    POSITIVE LOGITS
     pinulongan
    1.05
    AddHtmlAttribute
    0.83
    IVEREF
    0.81
    hoeddwyd
    0.79
    pushFollow
    0.77
     resourceCulture
    0.76
     typelib
    0.75
    numerusform
    0.71
    webElementGuid
    0.70
    saraba
    0.69
    Activations Density 7.609%

    No Known Activations