© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6688
    Prev
    Next
    INDEX
    Explanations

    clauses starting with the word "after" or "before"

    oai_token-act-pair · gemini-2.0-flash

    after before

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     nhiêu
    -0.48
    ính
    -0.48
    rizona
    -0.46
    ització
    -0.44
    itize
    -0.44
    anmoins
    -0.44
    nskap
    -0.44
     وأن
    -0.43
     refusé
    -0.43
     därför
    -0.43
    POSITIVE LOGITS
     becoming
    0.96
     taking
    0.94
     making
    0.93
     gaining
    0.93
     helping
    0.88
     getting
    0.88
     releasing
    0.87
     managing
    0.86
     giving
    0.86
     being
    0.84
    Activations Density 1.298%

    No Known Activations