© 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. 14817
    Prev
    Next
    INDEX
    Explanations

    words related to updating software

    oai_token-act-pair · gemini-2.0-flash

    updates and app features

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

    update

    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
     AssemblyCompany
    -0.67
     raiſ
    -0.64
    =$?
    -0.60
    MessageTagHelper
    -0.60
    modb
    -0.59
    ciatore
    -0.59
    thodon
    -0.57
    modelBuilder
    -0.54
     ſhe
    -0.54
    OrBuilder
    -0.54
    POSITIVE LOGITS
    styleable
    0.56
     обращения
    0.51
     records
    0.49
     un
    0.48
    屈
    0.47
    Un
    0.47
    gion
    0.46
     gloria
    0.45
     Bort
    0.45
    摘
    0.45
    Activations Density 12.011%

    No Known Activations