© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9393
    Prev
    Next
    INDEX
    Explanations

    this neuron looks for conversational text related to coding

    oai_token-act-pair · gemini-2.0-flash

    string concatenation syntax

    np_token-act-pair-logits · gpt-4o-mini

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     bit
    -0.91
     somewhat
    -0.77
    bit
    -0.74
    somewhat
    -0.65
    Bit
    -0.65
     kind
    -0.63
    kind
    -0.62
     quite
    -0.61
    Quite
    -0.61
     Quite
    -0.60
    POSITIVE LOGITS
     "+
    1.45
     '+
    1.41
    ("+
    1.33
    ('+
    1.26
    ="+
    1.17
     "+"
    1.16
    ='+
    1.16
    "+"
    1.14
    ">'+
    1.13
    '+
    1.10
    Activations Density 2.240%

    No Known Activations