© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9212
    Prev
    Next
    INDEX
    Explanations

    words related to software development

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to development frameworks

    np_token-act-pair-logits · gpt-4o-mini

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     canta
    -0.46
    enha
    -0.42
    åga
    -0.42
     newOwner
    -0.42
    CodeAnalysis
    -0.41
    GetKeyDown
    -0.41
     صرف
    -0.41
    usermodel
    -0.40
    द्धि
    -0.40
    trise
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.73
    SpringBootTest
    0.69
     estimés
    0.65
    thâu
    0.65
    ագրություններ
    0.63
    NewUrlParser
    0.61
    новниш
    0.60
     Ngb
    0.60
    agissait
    0.58
     Nightingale
    0.57
    Activations Density 5.724%

    No Known Activations