© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10317
    Prev
    Next
    INDEX
    Explanations

    computer programming related languages and terms

    oai_token-act-pair · gemini-2.0-flash

    coding languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     [*]
    -0.59
     Савез
    -0.56
    最快更新
    -0.55
    waitKey
    -0.54
    tí
    -0.49
     (.
    -0.49
     ${({
    -0.48
    glio
    -0.48
     Tenggara
    -0.48
     Hac
    -0.47
    POSITIVE LOGITS
    zzleHttp
    0.59
    lismo
    0.53
    RectangleBorder
    0.53
    COUVER
    0.53
     MaterialApp
    0.52
    lovakia
    0.52
    enderror
    0.51
     fieldNum
    0.50
    ifrance
    0.48
    +#+#
    0.48
    Activations Density 3.111%

    No Known Activations