© 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. 7074
    Prev
    Next
    INDEX
    Explanations

    terms related to computer graphics and video game performance settings

    oai_token-act-pair · gemini-2.0-flash

    Measurements or statistics

    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
    makeText
    -0.60
     comp
    -0.57
     doInBackground
    -0.56
    DrawerToggle
    -0.56
    CloseOperation
    -0.53
     di
    -0.48
    jface
    -0.47
     inf
    -0.46
    CppCodeGen
    -0.46
     Comp
    -0.46
    POSITIVE LOGITS
     firſt
    0.76
     Monfieur
    0.75
     Efq
    0.75
     beſt
    0.72
     whoſe
    0.71
     Reſ
    0.71
     Jefus
    0.69
     leaſt
    0.68
     preſent
    0.68
     Conſ
    0.68
    Activations Density 24.151%

    No Known Activations