© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12669
    Prev
    Next
    INDEX
    Explanations

    instances of two different languages (Spanish and Javascript) being used in the same document

    oai_token-act-pair · gemini-2.0-flash

    Spanish language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     of
    -0.81
     o
    -0.55
    enumi
    -0.49
    UrlResolution
    -0.44
     ot
    -0.38
     surla
    -0.37
     ο
    -0.35
    eadilan
    -0.35
     Drapeau
    -0.35
     о
    -0.35
    POSITIVE LOGITS
     de
    1.23
     del
    0.97
    دانشنامهٔ
    0.82
     '\\;'
    0.80
     dels
    0.79
    Demografía
    0.76
    FailureListener
    0.75
    XmlEnum
    0.75
    DoubleQuotes
    0.75
     سكانية
    0.75
    Activations Density 1.217%

    No Known Activations