© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11686
    Prev
    Next
    INDEX
    Explanations

    conjunctions, including foreign language conjunctions

    oai_token-act-pair · gemini-2.0-flash

    but

    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
    VolleyError
    -0.49
     division
    -0.49
    ZZO
    -0.49
    osis
    -0.48
    ACHED
    -0.48
    interopRequire
    -0.47
     lone
    -0.47
    genus
    -0.47
    urian
    -0.46
     Hols
    -0.46
    POSITIVE LOGITS
    <bos>
    0.81
     estekak
    0.66
    Демографія
    0.63
    Geplaatst
    0.59
    WireFormat
    0.57
     disambiguazione
    0.57
    RegressionTest
    0.57
    Demografie
    0.54
    ineno
    0.54
    NewUrlParser
    0.54
    Activations Density 1.358%

    No Known Activations