© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12442
    Prev
    Next
    INDEX
    Explanations

    verbs of creation and direction

    oai_token-act-pair · gemini-2.0-flash

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     RIPRODUZIONE
    -0.53
    zieli
    -0.52
     úteis
    -0.49
    fromnode
    -0.49
     Imperio
    -0.49
    ास्त
    -0.48
     mukana
    -0.47
     Seconde
    -0.47
    Termine
    -0.47
     unmarked
    -0.45
    POSITIVE LOGITS
     ostavi
    0.70
    Diwedd
    0.68
     >=",
    0.63
    ensement
    0.61
    TintMode
    0.60
    Cartney
    0.60
    writeFieldEnd
    0.60
    DeleteBehavior
    0.60
     EconPapers
    0.59
     faut
    0.59
    Activations Density 0.662%

    No Known Activations