© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8800
    Prev
    Next
    INDEX
    Explanations

    words that end in "k" or have some other association with darkness

    oai_token-act-pair · gemini-2.0-flash

    Cases of the letter "k"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    webElementXpaths
    -0.79
    verwijspagina
    -0.78
    ResumeLayout
    -0.77
    +:+
    -0.77
     autorytatywna
    -0.75
     createState
    -0.75
    DockStyle
    -0.73
     gynhyrchwyd
    -0.73
     незавершена
    -0.73
     فريبيس
    -0.73
    POSITIVE LOGITS
     dark
    1.02
    dark
    0.92
     Dark
    0.88
     darkness
    0.86
    Dark
    0.85
     DARK
    0.77
     darkest
    0.76
     oscuro
    0.71
    暗
    0.70
     暗
    0.69
    Activations Density 0.381%

    No Known Activations