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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16279
    Prev
    Next
    INDEX
    Explanations

    words and phrases that might appear in formal and informal writing, especially in regards to funding, laws, common phrases and opinions.

    oai_token-act-pair · gemini-2.0-flash

    "in" or "int"

    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
     propOrder
    -0.56
    Бахар
    -0.53
    endregion
    -0.53
     BoxFit
    -0.47
    consulté
    -0.47
    MessageState
    -0.46
     armat
    -0.45
     GetEnumerator
    -0.45
     cartaz
    -0.44
    Географија
    -0.44
    POSITIVE LOGITS
     i
    1.32
     int
    1.20
     inn
    0.95
     і
    0.93
     Int
    0.91
    int
    0.86
     ин
    0.85
     ints
    0.82
     iii
    0.82
    Int
    0.82
    Activations Density 2.712%

    No Known Activations