© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10757
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to have a large variety of activations, but they seem to be in the fields of file paths to code resources, medical/technical terms, and names/titles

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     al
    -0.50
     att
    -0.49
     Po
    -0.47
     et
    -0.45
     Stud
    -0.43
     Tag
    -0.42
     Fa
    -0.42
     Al
    -0.41
     Ver
    -0.40
     Sy
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.99
    IntoConstraints
    0.84
     дописавши
    0.78
     itſelf
    0.77
     autorytatywna
    0.76
     cherchés
    0.74
    webElementXpaths
    0.73
     myſelf
    0.73
     matel
    0.73
    حوالہ
    0.72
    Activations Density 0.959%

    No Known Activations