© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10446
    Prev
    Next
    INDEX
    Explanations

    words and phrases in Spanish related to programming concepts and reasoning

    oai_token-act-pair · gemini-2.0-flash

    y

    np_max-act · gemini-2.0-flash

    y

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Hochspringen
    -0.73
    مصادر
    -0.67
    NameInMap
    -0.61
     esternos
    -0.59
     Y
    -0.59
     snippetHide
    -0.57
    äldrar
    -0.55
     nonUne
    -0.55
     y
    -0.54
     חיצוניים
    -0.54
    POSITIVE LOGITS
    andExpect
    0.71
    oliber
    0.61
    مرار
    0.59
     Las
    0.58
    openqa
    0.56
     Mane
    0.56
    cipated
    0.56
     consom
    0.56
     ناب
    0.56
    danke
    0.55
    Activations Density 0.128%

    No Known Activations