© 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. 10492
    Prev
    Next
    INDEX
    Explanations

    poorly formatted scientific and mathematical notation with a lot of symbols

    oai_token-act-pair · gemini-2.0-flash

    Unusual characters/symbols

    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
    Hochspringen
    -0.69
    Datuak
    -0.61
     оригіналу
    -0.60
     AspNetCore
    -0.58
    帖最后由
    -0.57
     fiss
    -0.54
     يتيمه
    -0.54
    UNGEN
    -0.53
    ագրություններ
    -0.53
    mybatisplus
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.71
     Gnade
    0.61
    ureusement
    0.54
     harp
    0.50
     viewDidLoad
    0.49
     sebaliknya
    0.49
     Secured
    0.49
    QPalette
    0.48
    eramente
    0.47
     defaultstate
    0.47
    Activations Density 3.209%

    No Known Activations