© 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. 9915
    Prev
    Next
    INDEX
    Explanations

    technical writing, including research methodology, statistics, and references to other studies.

    oai_token-act-pair · gemini-2.0-flash

    addition

    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
    fre
    -0.42
    <b>
    -0.40
    masta
    -0.39
    ://
    -0.38
    TestingModule
    -0.38
    expandindo
    -0.38
    BagLayout
    -0.37
    fortawesome
    -0.37
    бин
    -0.36
     uma
    -0.36
    POSITIVE LOGITS
    
    0.93
    Personendaten
    0.78
    مصادر
    0.75
    ViewFeatures
    0.71
    olstadt
    0.71
     morire
    0.71
     betweenstory
    0.70
     BoxFit
    0.69
    TagMode
    0.68
     Савезне
    0.68
    Activations Density 34.619%

    No Known Activations