© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14698
    Prev
    Next
    INDEX
    Explanations

    words commonly used for sentimental content related to projects that are being showcased and the concept of cuteness

    oai_token-act-pair · gemini-2.0-flash

    commission

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Car
    -0.45
     Car
    -0.44
    il
    -0.44
    niv
    -0.44
    ilas
    -0.41
     بار
    -0.41
     testimonio
    -0.41
     acute
    -0.40
    politico
    -0.40
     arşivlendi
    -0.40
    POSITIVE LOGITS
    Commission
    1.05
     commissions
    1.02
     commission
    0.98
     Commission
    0.95
     Commissions
    0.94
    commission
    0.88
     himſelf
    0.81
     COMMISSION
    0.80
     themſelves
    0.80
     فريبيس
    0.79
    Activations Density 3.367%

    No Known Activations