© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4484
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words, but it especially likes proper nouns and words ending in "-ing," and "-ed."

    oai_token-act-pair · 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
    LLES
    -0.55
     DOING
    -0.54
    umenta
    -0.53
    modb
    -0.52
     trying
    -0.52
    initely
    -0.52
    enames
    -0.51
    PyObject
    -0.50
    asana
    -0.50
     doing
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.60
    ########.
    0.56
    PerformLayout
    0.51
     wiesz
    0.50
     Opt
    0.49
    Opt
    0.47
    ElementException
    0.46
    참고
    0.46
    VYMaps
    0.45
     JAXBElement
    0.45
    Activations Density 3.086%

    No Known Activations