© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10668
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive words that modify nouns and concepts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Alfons
    -0.51
    ̣ng
    -0.50
    szönöm
    -0.48
     fainting
    -0.48
     emerging
    -0.48
    estanding
    -0.48
     disappearing
    -0.47
     Dreyfus
    -0.47
    case
    -0.45
     fading
    -0.45
    POSITIVE LOGITS
    addCriterion
    0.70
    Hochspringen
    0.65
    modb
    0.63
    awtextra
    0.63
     ITIS
    0.63
    tonode
    0.62
    AnimationsModule
    0.61
     <=",
    0.60
     صوتيه
    0.60
    mybatisplus
    0.60
    Activations Density 5.261%

    No Known Activations