© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14596
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a limit or extreme

    oai_token-act-pair · gemini-2.0-flash

    Reaching an extreme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    깝
    -0.60
    fromCharCode
    -0.60
     ripar
    -0.57
     maintien
    -0.54
    umbersome
    -0.54
     FRONT
    -0.54
    ős
    -0.53
    Longest
    -0.53
    wanne
    -0.52
    }],
    -0.52
    POSITIVE LOGITS
    DockStyle
    0.69
    AutoScaleMode
    0.69
    aarrggbb
    0.68
     PLWABN
    0.65
    AntiForgeryToken
    0.64
     propOrder
    0.62
    ValueGenerated
    0.61
     насељу
    0.60
    SharedDtor
    0.59
     OMIT
    0.59
    Activations Density 1.166%

    No Known Activations