© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11840
    Prev
    Next
    INDEX
    Explanations

    the phrase "belong" or "belonged" followed by a preposition

    oai_token-act-pair · gemini-2.0-flash

    belong

    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
     aika
    -0.40
    an
    -0.39
    フリー
    -0.38
     contrast
    -0.37
    ซ
    -0.36
    contrast
    -0.35
     using
    -0.35
     past
    -0.35
     словарь
    -0.34
     vor
    -0.34
    POSITIVE LOGITS
    ReusableCell
    1.02
    belong
    0.87
    ]**
    0.84
    belongs
    0.82
    belongsTo
    0.81
    Rohy
    0.80
     FormGroup
    0.79
    DeleteBehavior
    0.78
     виправивши
    0.77
    setupUi
    0.77
    Activations Density 1.040%

    No Known Activations