© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13547
    Prev
    Next
    INDEX
    Explanations

    the word "lack"

    oai_token-act-pair · gemini-2.0-flash

    lack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     lack
    -0.93
    Lack
    -0.74
     Lack
    -0.74
    ds
    -0.66
    lack
    -0.59
     sfor
    -0.58
     المعيارى
    -0.57
    DS
    -0.54
     lacks
    -0.50
    fein
    -0.50
    POSITIVE LOGITS
     &___
    0.75
     resourceCulture
    0.74
    CreateMap
    0.71
    RuleContext
    0.70
     whoſe
    0.67
     considérons
    0.66
     Monfieur
    0.66
    NameInMap
    0.66
    makeConstraints
    0.65
     déput
    0.65
    Activations Density 0.301%

    No Known Activations