© 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. 5831
    Prev
    Next
    INDEX
    Explanations

    code-related keywords involving data types, object-oriented programming, and UI parameters

    oai_token-act-pair · gemini-2.0-flash

    code identifiers

    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
     announcement
    -1.74
     announcements
    -1.58
     announce
    -1.58
     announced
    -1.55
     announcing
    -1.52
     Announcement
    -1.43
     announces
    -1.39
     ANNOUNC
    -1.39
    announced
    -1.32
    announcement
    -1.26
    POSITIVE LOGITS
    m
    0.66
     m
    0.65
     &___
    0.60
    InjectAttribute
    0.59
     HasFactory
    0.58
    RetentionPolicy
    0.57
     pylint
    0.56
    TableHead
    0.53
    ModelAdmin
    0.53
    ValueStyle
    0.53
    Activations Density 1.004%

    No Known Activations