© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8888
    Prev
    Next
    INDEX
    Explanations

    words that end in -ed, -ing, -ly, words related to code as well as words that have to do with religion

    oai_token-act-pair · gemini-2.0-flash

    verbs ending in -ing/ed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    setVerticalGroup
    -0.82
     تضيفلها
    -0.77
    LEncoder
    -0.77
    ]--;
    -0.77
    EndContext
    -0.77
     AssemblyCompany
    -0.72
    ReusableCell
    -0.72
     елның
    -0.69
    }));
    -0.67
    AsUp
    -0.67
    POSITIVE LOGITS
     automatico
    0.52
     "..\..\..\
    0.49
     sape
    0.48
     automatiques
    0.47
     "..\..\
    0.47
     hôtes
    0.47
    kijken
    0.47
     came
    0.46
    Came
    0.46
    poietic
    0.46
    Activations Density 8.957%

    No Known Activations