© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11031
    Prev
    Next
    INDEX
    Explanations

    words related to terrorism and counter-terrorism efforts

    oai_token-act-pair · gemini-2.0-flash

    Encouraging

    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
     AttributeSet
    -0.70
    rungsseite
    -0.69
     '\\;'
    -0.65
    orsese
    -0.63
     sacrificio
    -0.58
     IFTT
    -0.58
     commerciali
    -0.58
    
    -0.57
     مرئيه
    -0.57
     يتيمه
    -0.56
    POSITIVE LOGITS
     encourage
    0.71
     nour
    0.66
     encouraging
    0.65
     encourages
    0.63
     support
    0.61
     feeds
    0.61
     encouragement
    0.59
     feeding
    0.59
     feed
    0.58
     supporting
    0.56
    Activations Density 2.185%

    No Known Activations