© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9566
    Prev
    Next
    INDEX
    Explanations

    the word "packed" when used to refer to spaces being full

    oai_token-act-pair · gemini-2.0-flash

    packed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     are
    -0.62
     has
    -0.56
     sul
    -0.53
     co
    -0.53
    NUMX
    -0.52
     is
    -0.51
     an
    -0.48
     strongly
    -0.47
    “
    -0.47
     XNUMX
    -0.46
    POSITIVE LOGITS
    تقاوى
    1.25
     saites
    0.95
     titolata
    0.95
    msgTypes
    0.92
    fjspx
    0.91
     AssemblyVersion
    0.91
     Seeder
    0.90
    Personensuche
    0.90
     AttributeSet
    0.89
    setVerticalGroup
    0.87
    Activations Density 1.691%

    No Known Activations