© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12439
    Prev
    Next
    INDEX
    Explanations

    the word "Big" followed by a number or a related word

    oai_token-act-pair · gemini-2.0-flash

    Big

    np_max-act-logits · 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
     big
    -1.58
    Big
    -1.53
    big
    -1.53
     Big
    -1.52
     BIG
    -1.38
    BIG
    -1.35
     bigger
    -0.77
    bigger
    -0.74
    大
    -0.72
     grosse
    -0.70
    POSITIVE LOGITS
     HasFactory
    0.74
    rawDesc
    0.71
    astify
    0.70
     AssemblyTitle
    0.69
    sizeCache
    0.68
     Audiodateien
    0.67
    rungsseite
    0.67
    rrggbb
    0.65
    Notae
    0.64
    ThroughAttribute
    0.61
    Activations Density 1.713%

    No Known Activations