© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13276
    Prev
    Next
    INDEX
    Explanations

    language related to terrorism, national security, and dangers

    oai_token-act-pair · gemini-2.0-flash

    co

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     word
    -2.02
    word
    -1.56
    Word
    -1.48
     WORD
    -1.39
     Word
    -1.37
    WORD
    -1.20
     palabra
    -1.07
     palavra
    -1.07
     woord
    -0.93
     parola
    -0.91
    POSITIVE LOGITS
     co
    3.34
     Co
    2.39
    Co
    2.22
    co
    2.22
     CO
    1.36
    CO
    1.30
     cof
    1.24
     Cob
    1.09
     coa
    1.02
     ко
    1.01
    Activations Density 3.944%

    No Known Activations