© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3230
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to small, compact, or reduced sizes.

    oai_token-act-pair · gemini-2.0-flash

    words related to size

    np_token-act-pair-logits · gpt-4o-mini

    small or compact

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     vectorielle
    -0.74
     AttributeSet
    -0.70
     AssemblyTitle
    -0.64
    
    -0.62
    Derbyniad
    -0.62
    rrggbb
    -0.60
    IsMutable
    -0.59
     препратки
    -0.59
    олові
    -0.59
     africaine
    -0.58
    POSITIVE LOGITS
     size
    1.33
     Size
    1.13
    size
    1.10
     sizes
    1.05
    Size
    1.03
     SIZE
    0.99
     tamaño
    0.93
     sized
    0.88
    SIZE
    0.87
     format
    0.84
    Activations Density 1.978%

    No Known Activations