© 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. 5178
    Prev
    Next
    INDEX
    Explanations

    words related to actions, states of being or feelings

    oai_token-act-pair · gemini-2.0-flash

    hybrid context markers and terms

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

    action

    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
     Italijani
    -0.56
     Glacial
    -0.51
     Cree
    -0.51
     Erster
    -0.49
     Noyes
    -0.48
     Taktlose
    -0.47
    gnore
    -0.45
     Peirce
    -0.45
     Pulver
    -0.44
    etzung
    -0.44
    POSITIVE LOGITS
    EndContext
    0.57
    MemoryWarning
    0.55
    Билгалдахарш
    0.54
    例文帳に追加
    0.54
    umbai
    0.51
     بيها
    0.51
     iconLine
    0.50
     jadx
    0.50
    İstinadlar
    0.50
     spalle
    0.49
    Activations Density 3.242%

    No Known Activations