© 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. 12936
    Prev
    Next
    INDEX
    Explanations

    what appear to be mostly unrelated fragments of text; it is difficult to give a short, meaningful description of what this neuron is doing

    oai_token-act-pair · 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
    mybatisplus
    -0.99
     CreateTagHelper
    -0.90
     autorytatywna
    -0.87
     Efq
    -0.86
     الحره
    -0.84
     snippetHide
    -0.84
    stdc
    -0.82
     Houſe
    -0.81
     Reſ
    -0.80
    حوالہ
    -0.79
    POSITIVE LOGITS
     
    0.49
     pas
    0.47
    .
    0.46
    ,
    0.46
    ↵
    0.44
     os
    0.42
    pas
    0.42
     me
    0.40
    LOYEES
    0.40
    ADJ
    0.40
    Activations Density 1.744%

    No Known Activations