© 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. 2186
    Prev
    Next
    INDEX
    Explanations

    words related to being in a court of law, and church meetings

    oai_token-act-pair · gemini-2.0-flash

    legal terminology related to dismissal

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

    Meetings and dismissals

    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
    tvguidetime
    -0.68
    kháu
    -0.66
     invokingState
    -0.66
    NewUrlParser
    -0.65
     disambiguazione
    -0.62
    TestingModule
    -0.61
    titleMargin
    -0.61
     <>",
    -0.60
     وتسجيلات
    -0.60
     typelib
    -0.60
    POSITIVE LOGITS
     dismiss
    0.48
     dismissed
    0.46
    ViewImports
    0.44
    adaptiveStyles
    0.43
    SharedDtor
    0.43
    caras
    0.42
     out
    0.42
    out
    0.42
     dismissal
    0.40
    ลา
    0.40
    Activations Density 1.212%

    No Known Activations