© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9230
    Prev
    Next
    INDEX
    Explanations

    words related to ranking or the first in a sequence

    oai_token-act-pair · gemini-2.0-flash

    mixed language/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    deleteById
    -0.58
    UpdatedBy
    -0.56
     actuelles
    -0.54
     RIPRODUZIONE
    -0.53
     infile
    -0.53
     relatifs
    -0.52
    Gemeinsame
    -0.52
    utup
    -0.52
    iddhar
    -0.51
     variés
    -0.50
    POSITIVE LOGITS
     first
    2.42
    first
    2.20
    First
    2.05
    FIRST
    1.95
     First
    1.95
     FIRST
    1.87
     pertama
    1.60
     eerste
    1.59
     primeira
    1.57
     erste
    1.51
    Activations Density 0.393%

    No Known Activations