© 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. 4574
    Prev
    Next
    INDEX
    Explanations

    clauses where something is lacking or not good

    oai_token-act-pair · gemini-2.0-flash

    cleanliness

    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
     صوتيه
    -0.54
    ylabel
    -0.49
    fxml
    -0.48
    CloseOperation
    -0.48
    reactivex
    -0.47
    jboss
    -0.47
    withOpacity
    -0.46
    arsky
    -0.45
    oslav
    -0.45
    createCanvas
    -0.45
    POSITIVE LOGITS
     cleanliness
    0.95
     cleanest
    0.79
     unclean
    0.78
     CLEAN
    0.77
     dirty
    0.77
     clean
    0.75
    Clean
    0.75
    clean
    0.73
     condition
    0.71
     tidy
    0.70
    Activations Density 0.768%

    No Known Activations