© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12297
    Prev
    Next
    INDEX
    Explanations

    text discussing the Unity and Visual Studio development environment

    oai_token-act-pair · gemini-2.0-flash

    Unity and Visual Studio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.20
     sanitaires
    -0.55
     réfrig
    -0.55
     forhold
    -0.55
     dispozici
    -0.54
     niečo
    -0.52
     accedere
    -0.52
    pozdrawiam
    -0.50
     funktioner
    -0.50
     řízení
    -0.49
    POSITIVE LOGITS
     UnityEditor
    1.14
     UnityEngine
    1.04
     WaitForSeconds
    1.02
    SerializeField
    0.94
     оригіналу
    0.88
     &___
    0.83
    makeText
    0.81
    GetAxis
    0.80
    ArgsConstructor
    0.79
    apimachinery
    0.79
    Activations Density 1.271%

    No Known Activations