© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2933
    Prev
    Next
    INDEX
    Explanations

    the letter "s" used as a variable name in code

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash

    ░▁s Method used: 1 — because MAX_ACTIVATING_TOKENS are identical — ▁s

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
    EDEFAULT
    -1.07
    LookAnd
    -1.02
    IsMutable
    -0.98
    клопе
    -0.92
    featureID
    -0.90
    KommentareTeilen
    -0.90
    makeText
    -0.87
    IndentedString
    -0.84
     AssemblyVersion
    -0.84
     CreateTagHelper
    -0.83
    POSITIVE LOGITS
     Jefus
    0.80
     becauſe
    0.77
     Theſe
    0.77
     Monfieur
    0.73
     deſt
    0.72
     pleaſure
    0.71
     ſta
    0.71
     cauſe
    0.71
    <bos>
    0.70
     ſhall
    0.70
    Activations Density 0.305%

    No Known Activations