© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6087
    Prev
    Next
    INDEX
    Explanations

    technical information for microcontroller based electronics projects

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming or data structures

    np_token-act-pair-logits · gpt-4o-mini

    Microcontrollers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    aroon
    -0.46
    ierto
    -0.46
    UIFont
    -0.45
     פי
    -0.45
    jstor
    -0.45
    ulco
    -0.44
    ahy
    -0.44
     dikel
    -0.44
     Boo
    -0.43
    wamy
    -0.43
    POSITIVE LOGITS
     AssemblyTitle
    0.80
    AddField
    0.66
     consultato
    0.64
     }}"></
    0.64
    SupportActionBar
    0.62
     CURIAM
    0.61
    esModule
    0.60
    ImageContext
    0.59
     ddelweddau
    0.58
     فريبيس
    0.57
    Activations Density 5.565%

    No Known Activations