© 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. 7556
    Prev
    Next
    INDEX
    Explanations

    words with a "den" prefix, particularly "denigrate" and "denuclearization" plus some that simply start with "den"

    oai_token-act-pair · gemini-2.0-flash

    den

    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
     den
    -0.98
    den
    -0.90
    Den
    -0.89
     Den
    -0.85
    DEN
    -0.78
    UnsafeEnabled
    -0.74
     DEN
    -0.73
     saites
    -0.64
    posedge
    -0.62
     AssemblyTitle
    -0.61
    POSITIVE LOGITS
    帖最后由
    0.58
     aveug
    0.50
     commerces
    0.50
     fédé
    0.49
     compéti
    0.49
    avx
    0.49
     frutta
    0.48
     refreshment
    0.47
     sauter
    0.47
     gouver
    0.46
    Activations Density 4.985%

    No Known Activations