© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11963
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded by a preposition or conjunction indicating a relationship between two elements or highlighting specific attributes

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

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

    Ordinal numbers

    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
    Personendaten
    -0.83
    FormTagHelper
    -0.64
    WebElementEntity
    -0.61
    RepeatedField
    -0.61
    Datuak
    -0.58
    تقاوى
    -0.57
    SerializedName
    -0.56
     Infórmanos
    -0.55
    __*/
    -0.54
    WriteTagHelper
    -0.54
    POSITIVE LOGITS
     sixth
    2.11
     fifth
    2.08
     seventh
    2.06
     ninth
    2.05
     third
    2.03
     fourth
    2.02
     eighth
    1.96
     tenth
    1.91
    third
    1.76
     eleventh
    1.73
    Activations Density 2.795%

    No Known Activations