© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8443
    Prev
    Next
    INDEX
    Explanations

    phrases denoting being in a location performing an action (e.g. "at home" or "outside")

    oai_token-act-pair · gemini-2.0-flash

    Locations, buildings, houses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    House
    -0.54
     House
    -0.52
     house
    -0.48
     domésticos
    -0.47
     doméstico
    -0.46
     Haus
    -0.46
     hall
    -0.46
     navideñas
    -0.46
    HOUSE
    -0.45
    المناصب
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.99
    MigrationBuilder
    0.88
    RegistryLite
    0.69
    utilisons
    0.68
     your
    0.67
     my
    0.66
    sidemargin
    0.66
    RegressionTest
    0.65
    StoryboardSegue
    0.63
     مشين
    0.60
    Activations Density 1.154%

    No Known Activations