© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10859
    Prev
    Next
    INDEX
    Explanations

    This neuron detects a combination of punctuation, symbols, numbers, and words related to letters.

    oai_token-act-pair · gemini-2.0-flash

    text editing/corrections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    VersionUID
    -0.54
    deleteById
    -0.52
     revision
    -0.52
    DrawerToggle
    -0.51
    ciech
    -0.50
     Reisedaten
    -0.49
     fug
    -0.44
     etern
    -0.44
    MessageOf
    -0.43
     bulle
    -0.42
    POSITIVE LOGITS
    :✨
    0.74
    RenderAtEndOf
    0.68
    sonian
    0.67
    WSGI
    0.64
    $_['
    0.63
    Portail
    0.59
    inscrire
    0.58
     métiers
    0.58
     препратки
    0.57
    AnchorTagHelper
    0.56
    Activations Density 2.260%

    No Known Activations