© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2912
    Prev
    Next
    INDEX
    Explanations

    references to the current or a specific week or days

    oai_token-act-pair · gemini-2.0-flash

    week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    CodeAnalysis
    -0.59
    Months
    -0.58
    hdysval
    -0.55
    Week
    -0.55
    UnitTesting
    -0.54
     Week
    -0.53
     hâte
    -0.51
     meses
    -0.49
     MonoBehaviour
    -0.48
     Himo
    -0.48
    POSITIVE LOGITS
     обе
    0.61
    IUrlHelper
    0.58
    Datuak
    0.58
    Демографія
    0.57
    &=&\
    0.56
    بوابة
    0.55
     Parkes
    0.55
    Baik
    0.55
     Versailles
    0.54
    tangentMode
    0.54
    Activations Density 1.347%

    No Known Activations