© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12987
    Prev
    Next
    INDEX
    Explanations

    words related to presenting ideas to formal groups.

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    sizeCache
    -0.58
    IsPostBack
    -0.56
    \{\\
    -0.55
    Przypisy
    -0.54
    
    -0.53
    enterio
    -0.47
     Normdatei
    -0.47
     声
    -0.46
     tartalomajánló
    -0.45
    angdong
    -0.44
    POSITIVE LOGITS
     for
    1.97
    for
    1.41
     For
    1.34
    For
    1.31
     FOR
    1.27
     для
    1.26
     voor
    1.16
     untuk
    1.13
     für
    1.09
    สำหรับ
    1.04
    Activations Density 2.936%

    No Known Activations