© 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. 10792
    Prev
    Next
    INDEX
    Explanations

    superlatives and words indicating importance

    oai_token-act-pair · gemini-2.0-flash

    largest

    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
     largest
    -1.63
    largest
    -1.57
     biggest
    -1.44
     highest
    -1.42
     longest
    -1.41
    biggest
    -1.41
     Largest
    -1.36
    highest
    -1.34
     smallest
    -1.33
     fastest
    -1.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.74
    EDEFAULT
    0.72
    twimg
    0.70
     esternos
    0.57
    XmlAccessType
    0.56
    mbal
    0.55
     TestBed
    0.54
    Източници
    0.54
     Chwiliwch
    0.52
     toArray
    0.51
    Activations Density 9.894%

    No Known Activations