© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14170
    Prev
    Next
    INDEX
    Explanations

    references to annual events and activities by organizations

    oai_token-act-pair · gemini-2.0-flash

    events and organizations

    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
     []:
    -0.47
     closely
    -0.46
     dura
    -0.44
    RAS
    -0.44
    viana
    -0.43
    ondere
    -0.42
    fclose
    -0.41
     measures
    -0.41
     appointments
    -0.40
    jska
    -0.40
    POSITIVE LOGITS
    contentLoaded
    0.82
    exitRule
    0.79
    ItemBackground
    0.78
    SharedCtor
    0.77
     utafitiHapana
    0.73
    quelize
    0.72
     EnglishChoose
    0.68
    oredCriteria
    0.68
    İstinadlar
    0.65
    NameInMap
    0.65
    Activations Density 1.575%

    No Known Activations