© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3260
    Prev
    Next
    INDEX
    Explanations

    places, institutions, and people's names

    oai_token-act-pair · gemini-2.0-flash

    sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     
    -0.42
    Keeper
    -0.40
    umbledore
    -0.40
     сосе
    -0.40
    addWidget
    -0.39
    hedrals
    -0.39
    vedev
    -0.38
     Keeper
    -0.38
    可惜
    -0.38
    chymal
    -0.36
    POSITIVE LOGITS
    Autoritní
    0.87
    LookAnd
    0.86
    contentLoaded
    0.82
    UnsafeEnabled
    0.80
    IsContent
    0.80
    Portail
    0.80
     getItemId
    0.79
     initComponents
    0.77
    ंदीखरीदारी
    0.77
    CodeAttribute
    0.77
    Activations Density 35.844%

    No Known Activations