© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1915
    Prev
    Next
    INDEX
    Explanations

    fragments of french text, especially those used in online chat

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    __":
    -0.61
     myself
    -0.55
    我和
    -0.54
     ourselves
    -0.51
     Ouverture
    -0.50
    glVertex
    -0.50
    cinogen
    -0.50
    __':
    -0.49
    addTo
    -0.49
    owicz
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.69
    saraba
    0.66
    enterOuterAlt
    0.61
     intéress
    0.58
    routeProvider
    0.58
    Бахар
    0.57
    ExecuteReader
    0.56
     hiér
    0.56
    Hentet
    0.55
    errHandler
    0.54
    Activations Density 3.173%

    No Known Activations