© 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. 14493
    Prev
    Next
    INDEX
    Explanations

    the characters "Je"

    oai_token-act-pair · gemini-2.0-flash

    tokens beginning with 'Je'

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

    Je

    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
    AddTagHelper
    -0.79
     nakalista
    -0.75
    yntaxException
    -0.64
     ligiloj
    -0.62
     unknownFields
    -0.61
    InjectMocks
    -0.61
    titleMargin
    -0.59
     ApiException
    -0.59
    Хьажоргаш
    -0.58
    EnableWeb
    -0.58
    POSITIVE LOGITS
    rungsseite
    0.58
    RenderAtEndOf
    0.56
    참고
    0.55
    opardy
    0.55
    bkz
    0.46
    SafeMath
    0.45
    MouseClicked
    0.44
     descu
    0.43
     ratify
    0.43
    multirow
    0.41
    Activations Density 0.363%

    No Known Activations