© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6001
    Prev
    Next
    INDEX
    Explanations

    programming related keywords like filetypes, directory names, and software

    oai_token-act-pair · gemini-2.0-flash

    software and file types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     TextInputType
    -0.97
     BoxDecoration
    -0.82
    دانشنامهٔ
    -0.82
    xase
    -0.80
     يتيمه
    -0.78
    GOTREF
    -0.77
     ***!
    -0.73
    WriteAttribute
    -0.73
     '\\;'
    -0.73
     CreateTagHelper
    -0.73
    POSITIVE LOGITS
     apellidos
    0.48
     Ruck
    0.43
    ESAR
    0.43
     Schedule
    0.41
    neus
    0.39
    Schedule
    0.39
    jsonwebtoken
    0.38
    ClientSize
    0.38
    抹
    0.37
    lesias
    0.37
    Activations Density 1.394%

    No Known Activations