© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9908
    Prev
    Next
    INDEX
    Explanations

    the letter "q" appearing inside or near programming code

    oai_token-act-pair · gemini-2.0-flash

    q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    q
    -1.91
     q
    -1.49
     Q
    -0.94
    Q
    -0.83
    qs
    -0.81
    qa
    -0.79
    ｑ
    -0.75
    ql
    -0.73
    qe
    -0.71
    qin
    -0.71
    POSITIVE LOGITS
     SUDOC
    0.70
     Roskov
    0.67
    ValueStyle
    0.67
     فريبيس
    0.66
    FormTagHelper
    0.64
     bourgeo
    0.63
    NewUrlParser
    0.61
    complexType
    0.59
    IsPostBack
    0.59
     AssemblyCulture
    0.59
    Activations Density 0.891%

    No Known Activations