© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5476
    Prev
    Next
    INDEX
    Explanations

    This neuron is matching stop words and some russian language fragments from stackoverflow

    oai_token-act-pair · gemini-2.0-flash

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    KommentareTeilen
    -0.79
    protoimpl
    -0.74
    MENAFN
    -0.71
     שוליים
    -0.68
     AssemblyCulture
    -0.68
    WebElementEntity
    -0.66
     []:
    -0.66
    UserScript
    -0.66
    AndEndTag
    -0.66
     فريبيس
    -0.65
    POSITIVE LOGITS
     GenerationType
    0.63
     reprendre
    0.53
     You
    0.49
    ledo
    0.46
     snabb
    0.45
     épaules
    0.45
    zzleHttp
    0.45
     девушки
    0.44
     мужчи
    0.43
    ResponseWriter
    0.43
    Activations Density 0.581%

    No Known Activations