© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13490
    Prev
    Next
    INDEX
    Explanations

    words related to international government organizations and counter-terrorism

    oai_token-act-pair · gemini-2.0-flash

    prefixes related to words about terrorism or security

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

    international agreements and organizations

    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
    yntaxException
    -0.73
     gynhyrchwyd
    -0.72
    LElement
    -0.72
    WaitGroup
    -0.71
     CreateTagHelper
    -0.69
    --){
    -0.68
     الحره
    -0.67
    GEBURTSDATUM
    -0.66
    +:+
    -0.63
    Groet
    -0.63
    POSITIVE LOGITS
    mul
    0.56
     box
    0.47
    mur
    0.46
    gre
    0.46
    UnsafeEnabled
    0.45
    chu
    0.45
    yal
    0.45
    ж
    0.44
    Gre
    0.44
    blu
    0.44
    Activations Density 3.250%

    No Known Activations