© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11030
    Prev
    Next
    INDEX
    Explanations

    the tokens "ag" and "atos", likely as part of a named entity

    oai_token-act-pair · gemini-2.0-flash

    location contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ')
    -0.41
           
    -0.41
     best
    -0.40
            
    -0.40
    </strong>
    -0.40
     دف
    -0.40
    sit
    -0.39
    Consider
    -0.39
    SneakyThrows
    -0.39
     qualsiasi
    -0.39
    POSITIVE LOGITS
    الحياه
    0.74
     ویکی‌پدیای
    0.73
    ValueStyle
    0.72
     EconPapers
    0.72
     kasarigan
    0.70
    parsedMessage
    0.70
     Мексичка
    0.68
     propOrder
    0.68
    nap
    0.68
    ArrowToggle
    0.67
    Activations Density 0.245%

    No Known Activations