© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13461
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of something

    oai_token-act-pair · gemini-2.0-flash

    lack or absence

    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
    liesslich
    -0.67
     nothing
    -0.53
     nowhere
    -0.53
    "{\
    -0.48
    .*")]
    -0.48
    BeginInit
    -0.47
    DockStyle
    -0.47
    nothing
    -0.46
    TagHelpers
    -0.46
     tantas
    -0.46
    POSITIVE LOGITS
     lack
    1.28
    lack
    0.95
     loss
    0.93
    Lack
    0.92
     Lack
    0.92
     absence
    0.89
     Absence
    0.82
    Loss
    0.81
     complete
    0.79
     manque
    0.79
    Activations Density 2.862%

    No Known Activations