© 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. 10990
    Prev
    Next
    INDEX
    Explanations

    a combination of words or phrases that are related to extremes, and also seems to focus heavily on the word "super".

    oai_token-act-pair · gemini-2.0-flash

    super

    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
     super
    -2.86
    super
    -2.77
    Super
    -2.75
     Super
    -2.69
     SUPER
    -2.42
    SUPER
    -2.28
     супер
    -1.83
    Супер
    -1.73
    超级
    -1.73
     súper
    -1.70
    POSITIVE LOGITS
    VolleyError
    0.54
    GridItem
    0.53
     Unsupported
    0.52
     springfox
    0.52
    QPalette
    0.51
    unjung
    0.51
     Za
    0.51
     mxArray
    0.51
     SEMESTER
    0.50
     Clips
    0.49
    Activations Density 8.311%

    No Known Activations