© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12788
    Prev
    Next
    INDEX
    Explanations

    a constellation of things including function definitions, the words "color" and "careers," and punctuation marks like colons and parentheses, so it seems this neuron is looking for code

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     kasarigan
    -0.72
     Signalez
    -0.71
     gynhyrchwyd
    -0.66
     elkaar
    -0.66
     AssemblyCulture
    -0.65
    دانشنامهٔ
    -0.63
     autorytatywna
    -0.61
    Ӕ
    -0.60
    󠁢
    -0.60
    ReusableCell
    -0.59
    POSITIVE LOGITS
    TagHelpers
    0.48
    Law
    0.42
    住
    0.39
    joueurs
    0.39
    reactstrap
    0.39
    ek
    0.38
    zk
    0.37
    ramo
    0.37
    endsection
    0.37
     meuble
    0.37
    Activations Density 0.501%

    No Known Activations