© 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. 11802
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and punctuation related to public events

    oai_token-act-pair · gemini-2.0-flash

    Events and Conferences

    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
    互联网档案馆
    -0.54
     AttributeSet
    -0.53
     StyleSheet
    -0.53
    TestBed
    -0.49
     Luz
    -0.49
    الإنجليزية
    -0.48
     Ush
    -0.48
     excerpt
    -0.48
     Ters
    -0.47
     opting
    -0.47
    POSITIVE LOGITS
    enciaga
    0.61
    SharedCtor
    0.60
     Roskov
    0.56
    NewRow
    0.53
     debate
    0.51
     hack
    0.49
     виправивши
    0.48
    tvguidetime
    0.47
     kiến
    0.46
    nthetic
    0.46
    Activations Density 3.462%

    No Known Activations