© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5904
    Prev
    Next
    INDEX
    Explanations

    words related to the process of requesting and responding to a request

    oai_token-act-pair · gemini-2.0-flash

    classifying data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     lenker
    -0.81
     незавершена
    -0.80
     صوتيه
    -0.76
    GIVEREF
    -0.76
    ViewImports
    -0.75
     otomatig
    -0.74
     للمعارف
    -0.73
    RegistryLite
    -0.72
    Datuak
    -0.71
     يتيمه
    -0.71
    POSITIVE LOGITS
    <bos>
    0.69
     the
    0.57
     a
    0.54
     and
    0.53
     your
    0.50
     his
    0.50
     certain
    0.48
     n
    0.45
     individual
    0.45
    Син
    0.44
    Activations Density 7.499%

    No Known Activations