© 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. 11839
    Prev
    Next
    INDEX
    Explanations

    the prefix "du" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the token 'du'

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

    du

    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
    bcryptjs
    -0.57
    |_
    -0.48
     proposons
    -0.48
     '\\;'
    -0.48
     proposées
    -0.48
     anledning
    -0.47
    mybatisplus
    -0.47
     successo
    -0.47
    Usos
    -0.46
     malheureux
    -0.46
    POSITIVE LOGITS
    principalTable
    0.66
     ExecuteAsync
    0.65
    '),
    0.56
    ftagPool
    0.56
    raska
    0.54
     مرئيه
    0.53
    ChildScrollView
    0.53
    ruptedException
    0.52
    Portail
    0.52
    sphase
    0.52
    Activations Density 0.266%

    No Known Activations