© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6152
    Prev
    Next
    INDEX
    Explanations

    lines starting with 'package', 'import', or 'org' in Java code

    oai_token-act-pair · gemini-2.0-flash

    import

    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
     kasarigan
    -0.80
     makeStyles
    -0.69
     ſtate
    -0.66
     pleaſure
    -0.60
     uſe
    -0.59
     uſ
    -0.59
    getSeconds
    -0.59
    neſs
    -0.59
    ########.
    -0.58
    modelBuilder
    -0.57
    POSITIVE LOGITS
    UIControlState
    0.61
     static
    0.47
     lij
    0.45
    granate
    0.44
    atia
    0.44
     Multi
    0.43
    eload
    0.42
    veret
    0.42
     Himo
    0.41
     poco
    0.41
    Activations Density 0.173%

    No Known Activations