© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    mathematical equations with partial derivatives

    oai_token-act-pair · gemini-2.0-flash

    partial

    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
    сылкі
    -0.77
     Kitch
    -0.66
    الإنجليزية
    -0.65
     peine
    -0.65
     EconPapers
    -0.65
    EndProject
    -0.63
    تقاوى
    -0.60
    gameserver
    -0.59
    ConstraintMaker
    -0.59
     للاسماء
    -0.59
    POSITIVE LOGITS
    .
    0.60
    ,
    0.52
    而言
    0.43
    ="/">
    0.43
    pias
    0.41
    Thunk
    0.41
    平时
    0.40
    र्ड
    0.40
    The
    0.40
     (
    0.40
    Activations Density 1.499%

    No Known Activations