© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4562
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to identify programming-related content, specifically code, data structures, and algorithms.

    oai_token-act-pair · gemini-2.0-flash

    contains

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    oa̍t
    -0.56
     picioare
    -0.55
    GroupLayout
    -0.53
     ympä
    -0.49
     pulley
    -0.49
     Menge
    -0.47
     Económica
    -0.46
     lemn
    -0.45
    rifuge
    -0.45
     Sélectionnez
    -0.44
    POSITIVE LOGITS
     contains
    0.74
     containing
    0.70
     contient
    0.68
    contains
    0.67
    ++]=
    0.65
     الدولى
    0.64
     contain
    0.63
    ++]
    0.62
    ++];
    0.62
    arynge
    0.60
    Activations Density 4.326%

    No Known Activations