© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13635
    Prev
    Next
    INDEX
    Explanations

    words related to governmental authority, legal proceedings, and law enforcement

    oai_token-act-pair · gemini-2.0-flash

    welcome

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    osoba
    -0.54
    Portály
    -0.53
    NameInMap
    -0.52
    .*")]
    -0.52
    andExpect
    -0.51
    migrationBuilder
    -0.51
    oneofs
    -0.50
    tvguidetime
    -0.50
    XmlAccessType
    -0.50
    WebServlet
    -0.50
    POSITIVE LOGITS
     welcome
    1.89
     welcomed
    1.73
     welcomes
    1.63
    welcome
    1.58
     Welcome
    1.58
     welcoming
    1.56
     WELCOME
    1.53
    Welcome
    1.43
    WELCOME
    1.29
    wel
    1.20
    Activations Density 3.119%

    No Known Activations