© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6609
    Prev
    Next
    INDEX
    Explanations

    scientific writing discussing diffusion, particularly with related terms and equations.

    oai_token-act-pair · gemini-2.0-flash

    diffusion

    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
    thday
    -0.70
    fjspx
    -0.69
     său
    -0.69
     wußte
    -0.64
     natale
    -0.63
     ainfi
    -0.62
     touristes
    -0.61
    PerformLayout
    -0.60
     Насе
    -0.59
    舺
    -0.59
    POSITIVE LOGITS
    DataPropertyName
    0.52
     Meksiku
    0.45
     effects
    0.45
     Процитовано
    0.44
     process
    0.44
     processes
    0.43
    FieldDescriptor
    0.41
     efficiency
    0.41
    شاركة
    0.41
    Bakgrunnsstoff
    0.40
    Activations Density 4.833%

    No Known Activations