© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9687
    Prev
    Next
    INDEX
    Explanations

    commas, conjunctions, and interjections within narrative text

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     المعيارى
    -0.63
     nemlig
    -0.59
     étoient
    -0.57
     étoit
    -0.56
    енча
    -0.55
    eseorang
    -0.53
    forRoot
    -0.51
     culturelles
    -0.50
     avoient
    -0.50
     ausged
    -0.48
    POSITIVE LOGITS
    ruptedException
    0.60
     feeling
    0.59
     wanting
    0.58
     seeking
    0.56
    tagext
    0.56
     offering
    0.55
     unable
    0.53
    OGND
    0.53
     needing
    0.51
    posedge
    0.51
    Activations Density 1.973%

    No Known Activations