© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12511
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships, especially marriage, motherhood and celebrity couples

    oai_token-act-pair · gemini-2.0-flash

    celebrity events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    \{\\
    -0.73
     مشين
    -0.69
     againſt
    -0.63
     whoſe
    -0.63
     MenuView
    -0.61
    ranean
    -0.61
    Ikus
    -0.61
    )++;
    -0.60
     Quattro
    -0.60
     Etr
    -0.60
    POSITIVE LOGITS
    subpackage
    0.50
     diện
    0.49
     parar
    0.45
    check
    0.45
    ModelForm
    0.45
    chement
    0.44
     thể
    0.42
     check
    0.42
    update
    0.41
    io
    0.40
    Activations Density 0.633%

    No Known Activations