© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12648
    Prev
    Next
    INDEX
    Explanations

    words relating to chemistry, biology, and plumbing

    oai_token-act-pair · gemini-2.0-flash

    Degrading (enzymes/materials/chemicals)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    calaureate
    -0.58
    MarshalTo
    -0.50
    shadowOpacity
    -0.48
    atars
    -0.48
    
    -0.48
     tradition
    -0.46
    ftal
    -0.46
    <bos>
    -0.46
    WebVitals
    -0.45
    ViewFeatures
    -0.44
    POSITIVE LOGITS
     mittens
    0.53
    zess
    0.53
     aikaa
    0.53
     rộng
    0.52
    ,:);
    0.51
     løpet
    0.50
    mybatisplus
    0.50
     pulizia
    0.49
     strøm
    0.49
    featureID
    0.49
    Activations Density 2.083%

    No Known Activations