© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    biomedical research and procedures, especially involving controls and experiments

    oai_token-act-pair · gemini-2.0-flash

    control

    np_max-act-logits · 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
    SharedDtor
    -0.58
     متعلقه
    -0.57
    ModelSerializer
    -0.56
     AspNetCore
    -0.55
    createClass
    -0.54
    InstanceState
    -0.52
    httphttps
    -0.51
     <<<<<<<<<<<<<<
    -0.50
    脚注の使い方
    -0.50
    usermodel
    -0.50
    POSITIVE LOGITS
     control
    2.77
     Control
    2.48
    control
    2.39
    Control
    2.36
     controls
    2.34
     CONTROL
    2.20
    CONTROL
    2.09
     Controls
    2.09
     contrôle
    1.98
    controls
    1.93
    Activations Density 4.949%

    No Known Activations