© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2202
    Prev
    Next
    INDEX
    Explanations

    substrings that are parts of words, particularly related to place names, chemicals, magazines and things that sound like chemicals to it

    oai_token-act-pair · gemini-2.0-flash

    Magazine descriptions/documentation

    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
     CGRectMake
    -0.60
     loud
    -0.53
     iron
    -0.52
    findpost
    -0.50
    исленность
    -0.50
     hall
    -0.48
     Iron
    -0.48
     Hall
    -0.47
     Valley
    -0.46
    Hall
    -0.45
    POSITIVE LOGITS
     Chwiliwch
    0.74
     يتيمه
    0.73
     Wiktionnaire
    0.72
    AddTagHelper
    0.71
    IUrlHelper
    0.66
    ########.
    0.65
    ftagPool
    0.65
    oredCriteria
    0.63
    dafx
    0.63
     CreateTagHelper
    0.62
    Activations Density 9.667%

    No Known Activations