© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10884
    Prev
    Next
    INDEX
    Explanations

    financial information, especially losses

    oai_token-act-pair · gemini-2.0-flash

    uncommon or nonsensical tokens

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

    Large numbers and geopolitical events

    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
    AddHtmlAttribute
    -0.65
    GOTREF
    -0.63
    basicConfig
    -0.57
    ImageContext
    -0.57
    مصادر
    -0.56
    Попис
    -0.55
    الحياه
    -0.54
     BNE
    -0.54
     SwitchCompat
    -0.53
    ariado
    -0.52
    POSITIVE LOGITS
     Tiên
    0.47
    tschafts
    0.46
     quebra
    0.46
    一目
    0.46
    ="@+
    0.43
     tør
    0.42
    Bakgrunnsstoff
    0.41
    BREAK
    0.41
    Predecesor
    0.41
    Skocz
    0.40
    Activations Density 1.069%

    No Known Activations