© 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. 12495
    Prev
    Next
    INDEX
    Explanations

    a mix of terms having to do with broadcasting, lists, years, and death

    oai_token-act-pair · gemini-2.0-flash

    broadcasting

    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
    hup
    -0.45
     bety
    -0.45
    向
    -0.43
     useParams
    -0.41
     CGRect
    -0.41
     early
    -0.40
     /\.
    -0.39
    త
    -0.39
     submitted
    -0.39
    ěstí
    -0.38
    POSITIVE LOGITS
    ptonshire
    0.68
    Personendaten
    0.65
     ویکی‌پدی
    0.64
     Италијани
    0.63
     ivelany
    0.63
    Panamoan
    0.63
     InputDecoration
    0.62
    seamnă
    0.61
     wireType
    0.61
    cardname
    0.61
    Activations Density 0.459%

    No Known Activations