© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15024
    Prev
    Next
    INDEX
    Explanations

    code or code-related terms like imports, definitions, system calls, and testing functions

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    aarrggbb
    -0.60
    bkz
    -0.59
    ReusableCell
    -0.58
     LUMP
    -0.57
    TagHelper
    -0.55
     مفص
    -0.52
    findpost
    -0.51
    PMailer
    -0.50
    GraphicsUnit
    -0.50
    HasColumnName
    -0.50
    POSITIVE LOGITS
     jsPsych
    0.59
    unknownFields
    0.53
     kiin
    0.50
     StatefulWidget
    0.50
     ",";
    0.50
     Genome
    0.50
    perties
    0.50
     Deckel
    0.50
     Houghton
    0.50
    economics
    0.49
    Activations Density 1.177%

    No Known Activations