© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12440
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "French," and to a far lesser extent, "France" and "Pacific".

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AndEndTag
    -0.71
    #+#
    -0.63
     يتيمه
    -0.56
     Мексичка
    -0.56
    CPL
    -0.50
    protoc
    -0.49
    Datuak
    -0.48
    jinal
    -0.48
    SequentialGroup
    -0.48
     Meksiku
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.67
    EndContext
    0.59
    homonymie
    0.58
     Wiktionnaire
    0.53
    XmlAttribute
    0.51
    Jereo
    0.50
     Exacts
    0.50
    autorité
    0.49
    cần
    0.48
    ACHUSETTS
    0.48
    Activations Density 0.334%

    No Known Activations