© 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. 10124
    Prev
    Next
    INDEX
    Explanations

    the phrases "belong to" and code-related terms

    oai_token-act-pair · gemini-2.0-flash

    "belong" or code snippets

    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
    belong
    -1.44
     belong
    -1.44
     belongs
    -1.40
     belonging
    -1.31
     belonged
    -1.30
    belongs
    -1.27
     Belong
    -1.25
     pertenece
    -1.05
     pertence
    -1.03
     perten
    -1.00
    POSITIVE LOGITS
    IUrlHelper
    0.51
     v
    0.39
    との
    0.36
     surla
    0.36
     yeterli
    0.36
    pageX
    0.35
    an
    0.35
     present
    0.34
    フリー
    0.34
     tr
    0.33
    Activations Density 1.279%

    No Known Activations