© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10144
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating the endurance, continuation, or maintenance of something

    oai_token-act-pair · gemini-2.0-flash

    survive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    μος
    -0.60
    Descripció
    -0.59
     DialogInterface
    -0.56
    ative
    -0.55
    rasz
    -0.52
    atory
    -0.52
     capas
    -0.52
    
    -0.52
     Alca
    -0.52
    性的
    -0.52
    POSITIVE LOGITS
     obicei
    0.60
     liggen
    0.59
     IndexPath
    0.58
    icap
    0.58
    getBean
    0.58
    GEBURTSDATUM
    0.56
     illustrationer
    0.54
     caduta
    0.54
    getInputStream
    0.53
    Dziękuję
    0.53
    Activations Density 2.501%

    No Known Activations