© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11442
    Prev
    Next
    INDEX
    Explanations

    words ending in "el," especially those with Latinate or scientific origins or related to political maneuvering and news reporting.

    oai_token-act-pair · gemini-2.0-flash

    crystal structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    으로
    -0.87
    less
    -0.75
    LESS
    -0.59
    ları
    -0.57
    land
    -0.56
    ELESS
    -0.56
    ians
    -0.56
    ness
    -0.54
    upuncture
    -0.54
    ⓧ
    -0.53
    POSITIVE LOGITS
    led
    1.43
    LED
    0.88
    ll
    0.68
    leda
    0.66
     led
    0.66
    lia
    0.63
     MainAxisSize
    0.61
    let
    0.60
    lie
    0.60
    lable
    0.60
    Activations Density 3.724%

    No Known Activations