© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4815
    Prev
    Next
    INDEX
    Explanations

    various code syntax, including array assignments and declarations, and some variable names related to images.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    MigrationBuilder
    -0.84
    SourceChecksum
    -0.81
     CreateTagHelper
    -0.79
    EDEFAULT
    -0.78
     HasFactory
    -0.76
     ModelExpression
    -0.75
     Waray
    -0.73
     Wikimedijinoj
    -0.73
     createState
    -0.71
    InstanceState
    -0.69
    POSITIVE LOGITS
    olge
    0.47
     surla
    0.45
    водство
    0.40
     Flügel
    0.39
     inclusion
    0.39
     Vergine
    0.39
     národ
    0.39
     pro
    0.38
     power
    0.38
     obviously
    0.37
    Activations Density 10.715%

    No Known Activations