© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16360
    Prev
    Next
    INDEX
    Explanations

    references to roads, highways, and government bodies that oversee them, as well as dates, especially years.

    oai_token-act-pair · gemini-2.0-flash

    highway construction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    گرد
    -0.50
    spec
    -0.47
     spé
    -0.46
     cing
    -0.46
    Film
    -0.45
     Spec
    -0.45
    igli
    -0.44
    ParseException
    -0.43
    desen
    -0.42
     vrst
    -0.42
    POSITIVE LOGITS
    PhysRevD
    0.78
     LUMP
    0.76
     AssemblyCulture
    0.69
     Roskov
    0.66
    ABUL
    0.66
    RTLD
    0.64
    Rohy
    0.64
     تانيه
    0.64
    Хьажоргаш
    0.63
    :✨
    0.63
    Activations Density 2.199%

    No Known Activations