© 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. 4950
    Prev
    Next
    INDEX
    Explanations

    lines that consist only of whitespace

    oai_token-act-pair · gemini-2.0-flash

    non-English words or phrases

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

    non-English

    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
     
    -0.47
     t
    -0.46
     ger
    -0.45
     che
    -0.41
     all
    -0.41
     c
    -0.40
     [
    -0.40
    t
    -0.40
     Ger
    -0.37
     ‘
    -0.37
    POSITIVE LOGITS
     صوتيه
    1.15
     متعلقه
    0.99
    脚注の使い方
    0.94
     ddelweddau
    0.93
     المعيارى
    0.91
    
    0.87
     nahilalakip
    0.85
     незавершена
    0.82
    Aktualisiert
    0.82
     HasFactory
    0.81
    Activations Density 0.086%

    No Known Activations