© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10971
    Prev
    Next
    INDEX
    Explanations

    sentences where something is described as too much, too little, or too long

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    larger
    -1.65
     Larger
    -1.64
    higher
    -1.62
    Larger
    -1.61
     larger
    -1.57
    Higher
    -1.55
     older
    -1.55
    Older
    -1.53
    smaller
    -1.52
     heavier
    -1.50
    POSITIVE LOGITS
    jTextField
    0.47
     least
    0.44
    oooooooooooooooo
    0.41
    <%=
    0.41
    anged
    0.40
    othea
    0.40
    Cormack
    0.40
    corrhi
    0.39
    conazole
    0.39
    oren
    0.39
    Activations Density 5.955%

    No Known Activations