© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2823
    Prev
    Next
    INDEX
    Explanations

    attribution in news articles, as well as formatting and punctuation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     investigators
    -0.65
     investigator
    -0.63
     investigations
    -0.63
     police
    -0.63
     crime
    -0.62
     investigation
    -0.60
     crimes
    -0.59
     criminal
    -0.56
     prosecutors
    -0.56
     investigative
    -0.56
    POSITIVE LOGITS
     désolés
    0.69
    存于互联网档案馆
    0.68
    DECREF
    0.68
    BASEPATH
    0.64
    хьтан
    0.60
     WaitForSeconds
    0.59
    ciamo
    0.57
    цездатний
    0.56
     مواليد
    0.56
     الحره
    0.56
    Activations Density 8.489%

    No Known Activations