© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4161
    Prev
    Next
    INDEX
    Explanations

    words related to technology, software, services, and support, sometimes within the specific context of Amazon Web Services (AWS).

    oai_token-act-pair · gemini-2.0-flash

    Negative situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Referències
    -0.73
     propOrder
    -0.66
     typelib
    -0.65
     المعيارى
    -0.65
    huber
    -0.63
     Paglinawan
    -0.63
     Normdatei
    -0.61
     ویکی‌پدیای
    -0.61
    FormTagHelper
    -0.58
    مقاله
    -0.57
    POSITIVE LOGITS
    MigrationBuilder
    0.58
    WebControls
    0.52
    __":
    0.49
    __':
    0.48
    awaiter
    0.46
    
    0.45
    __':
    0.45
    rang
    0.44
    writeField
    0.43
     Italijanski
    0.43
    Activations Density 33.168%

    No Known Activations