© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10129
    Prev
    Next
    INDEX
    Explanations

    text in Spanish or Portuguese containing accents, and also finds the word "ajedrez"

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    IntoConstraints
    -0.69
     Efq
    -0.65
     فريبيس
    -0.65
    VIAF
    -0.62
     againſt
    -0.62
    fromnode
    -0.59
    переди
    -0.59
     iprot
    -0.57
     billed
    -0.57
     InputDecoration
    -0.57
    POSITIVE LOGITS
    if
    0.64
     but
    0.63
     which
    0.58
     whether
    0.58
    but
    0.57
     that
    0.56
     if
    0.56
     such
    0.55
     why
    0.55
     what
    0.50
    Activations Density 0.458%

    No Known Activations