© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 230
    Prev
    Next
    INDEX
    Explanations

    the letter 'n' and words related to size within code snippets

    oai_token-act-pair · gemini-2.0-flash

    n

    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
    Negative Logits
    n
    -1.69
     n
    -1.68
    IsContent
    -0.89
    <bos>
    -0.84
    ｎ
    -0.84
    N
    -0.83
     N
    -0.81
    setN
    -0.80
    nA
    -0.75
    nC
    -0.71
    POSITIVE LOGITS
    MemoryWarning
    0.57
    TestingModule
    0.49
    apunov
    0.47
    hassee
    0.46
    arsch
    0.46
     Meadows
    0.44
    INH
    0.44
    autoIncrement
    0.44
    entiel
    0.43
    manship
    0.43
    Activations Density 3.345%

    No Known Activations