© 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. 14683
    Prev
    Next
    INDEX
    Explanations

    features of Swift and Kotlin code.

    oai_token-act-pair · gemini-2.0-flash

    code keywords

    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
     Normdatei
    -1.05
    Geplaatst
    -0.75
     lenker
    -0.75
    RUnlock
    -0.75
    sizeCache
    -0.72
    WriteBarrier
    -0.72
    writeField
    -0.71
    AnimationsModule
    -0.71
     springfox
    -0.67
    +#+#
    -0.64
    POSITIVE LOGITS
     default
    0.50
    ofte
    0.49
     sight
    0.47
    ảnh
    0.46
    Fault
    0.46
    repe
    0.46
    async
    0.45
    default
    0.44
    foreground
    0.44
    leng
    0.44
    Activations Density 1.911%

    No Known Activations