© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4117
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express a contrast between a problem and the means to solve that problem with more focus on the problem.

    oai_token-act-pair · gemini-2.0-flash

    play and toys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    +#+
    -0.73
    AndroidJUnit
    -0.68
    openzeppelin
    -0.67
    SequentialGroup
    -0.64
    ToBounds
    -0.60
    fastjson
    -0.59
    CloseOperation
    -0.59
    arResult
    -0.59
    LinkId
    -0.58
     délib
    -0.57
    POSITIVE LOGITS
    出版年
    0.74
    fromnode
    0.56
    kháu
    0.53
    ValueStyle
    0.50
    تقاوى
    0.50
    THISDAY
    0.47
    KURZBESCHREIBUNG
    0.47
    Хьажоргаш
    0.46
    Lähteet
    0.45
     ویکی‌پدی
    0.44
    Activations Density 15.428%

    No Known Activations