© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6218
    Prev
    Next
    INDEX
    Explanations

    sentences that include the word "one", other pronouns, or words indicating responsibility

    oai_token-act-pair · gemini-2.0-flash

    one

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    RegistryLite
    -0.69
    Espèce
    -0.67
    RegressionTest
    -0.66
    γραφία
    -0.66
    UnknownFieldSet
    -0.63
    annica
    -0.63
    yntaxException
    -0.61
    ViewFeatures
    -0.59
    TabIndex
    -0.59
    หว่าง
    -0.59
    POSITIVE LOGITS
     coûte
    0.51
     anyway
    0.50
     pertenecen
    0.49
    .
    0.49
    ;
    0.47
    IsContent
    0.47
    !
    0.47
     anyways
    0.47
     because
    0.46
     graças
    0.45
    Activations Density 4.984%

    No Known Activations