© 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. 10651
    Prev
    Next
    INDEX
    Explanations

    idioms and legal/medical language

    oai_token-act-pair · gemini-2.0-flash

    advantage or disadvantage

    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
     виправивши
    -0.65
    ViewFeatures
    -0.58
     תע
    -0.54
    ="#"
    -0.53
    ="/"
    -0.53
    ="/">
    -0.52
    invokeLater
    -0.52
     OnTriggerEnter
    -0.49
    RetentionPolicy
    -0.49
    InSection
    -0.49
    POSITIVE LOGITS
     Favor
    0.66
    Fav
    0.62
     favor
    0.61
     favour
    0.60
    Favor
    0.60
     favoring
    0.60
     favorable
    0.59
     Fav
    0.59
     favourable
    0.58
    مصادر
    0.57
    Activations Density 0.907%

    No Known Activations