© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 78
    Prev
    Next
    INDEX
    Explanations

    dates and business-related proclamations.

    oai_token-act-pair · gemini-2.0-flash

    News/Announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     المعيارى
    -0.91
    aarrggbb
    -0.79
    IVEREF
    -0.74
    InputTagHelper
    -0.71
    Espèce
    -0.70
    ]")]
    -0.69
    OGND
    -0.68
     يتيمه
    -0.68
    AutoField
    -0.67
     nakalista
    -0.67
    POSITIVE LOGITS
    vaig
    0.41
     exemplu
    0.40
    useEffect
    0.40
    bindParam
    0.40
    verwijspagina
    0.38
    把手
    0.38
     princesas
    0.38
     सकती
    0.36
    endorong
    0.36
    ortable
    0.35
    Activations Density 1.737%

    No Known Activations