© 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. 8896
    Prev
    Next
    INDEX
    Explanations

    a detailed sequence of an arrest by undercover agents

    oai_token-act-pair · gemini-2.0-flash

    uncommon words from multiple languages

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

    arrests and crime

    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
    OGND
    -0.78
    TestTools
    -0.75
     विश्वसनीयता
    -0.68
    MLLoader
    -0.66
    WebElementEntity
    -0.65
     sauer
    -0.64
    SharedDtor
    -0.64
     Италијани
    -0.64
     bastard
    -0.62
    richTextPanel
    -0.62
    POSITIVE LOGITS
     gomma
    0.48
     subjects
    0.47
     Wiktionnaire
    0.46
    rungsseite
    0.42
    wyt
    0.41
     pregi
    0.41
     iVar
    0.40
     كومونز
    0.40
     nacionais
    0.40
     œufs
    0.40
    Activations Density 2.701%

    No Known Activations