© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12214
    Prev
    Next
    INDEX
    Explanations

    terms, conditions, and licenses related to copyright and open source usage

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Sp
    -0.62
    <0xE2>
    -0.57
     Sp
    -0.54
    ese
    -0.54
    Sh
    -0.49
    Au
    -0.49
    ele
    -0.49
    ​
    -0.49
    Ma
    -0.49
    of
    -0.48
    POSITIVE LOGITS
     الحره
    1.02
     فريبيس
    0.98
     سكانية
    0.95
     كومونز
    0.95
     ویکی‌آمباردا
    0.91
    Personensuche
    0.91
     tartalomajánló
    0.91
    Datuak
    0.90
    NewUrlParser
    0.87
    ✨:
    0.86
    Activations Density 3.498%

    No Known Activations