© 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. 5344
    Prev
    Next
    INDEX
    Explanations

    the name "John", sometimes followed by a middle initial or a last name

    oai_token-act-pair · gemini-2.0-flash

    the name 'John'

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

    John

    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
    DebuggerStep
    -0.60
    
    -0.54
     ExecuteAsync
    -0.53
    JdbcTemplate
    -0.52
    @[+][
    -0.52
    AccessFile
    -0.52
    ậu
    -0.52
    期刊论文
    -0.51
    XtraGrid
    -0.51
    حوالہ
    -0.50
    POSITIVE LOGITS
     colspan
    0.49
    ebenarnya
    0.47
     الدولى
    0.47
     ayude
    0.45
     ziren
    0.45
    sweise
    0.44
    qrt
    0.43
     للتو
    0.43
     proviene
    0.43
    seamnă
    0.42
    Activations Density 0.275%

    No Known Activations