© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8091
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and discourse markers

    oai_token-act-pair · gemini-2.0-flash

    I

    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
    ]-->
    -0.43
     encargada
    -0.43
     AssemblyCulture
    -0.42
     inappropriés
    -0.42
     wala
    -0.41
    Explicación
    -0.41
    Condol
    -0.40
    resumen
    -0.40
    unków
    -0.39
    ∎
    -0.39
    POSITIVE LOGITS
    EDEFAULT
    0.70
    ResponseWriter
    0.62
    OCCURRED
    0.60
    ="@+
    0.60
     AssemblyVersion
    0.59
     Generales
    0.59
    الحياه
    0.59
    KommentareTeilen
    0.58
    dropIfExists
    0.58
    rouch
    0.58
    Activations Density 6.573%

    No Known Activations