© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5895
    Prev
    Next
    INDEX
    Explanations

    code related to equality checks with a bias towards the letter "o"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.41
    ’
    -0.68
     contactez
    -0.52
     XNUMX
    -0.50
    bertas
    -0.50
    openqa
    -0.50
    вЂ
    -0.50
     vostri
    -0.49
     Contactez
    -0.48
    '
    -0.48
    POSITIVE LOGITS
     دیکھیے
    0.81
    tagHelperRunner
    0.80
     propOrder
    0.80
     nahilalakip
    0.78
    intios
    0.77
     intStringLen
    0.75
    GEBURTSDATUM
    0.74
     beginnetje
    0.73
    principalTable
    0.73
     EconPapers
    0.73
    Activations Density 9.157%

    No Known Activations