© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15937
    Prev
    Next
    INDEX
    Explanations

    types of meat, especially pork

    oai_token-act-pair · gemini-2.0-flash

    meat context

    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
    UnusedPrivate
    -0.79
    AnchorStyles
    -0.73
     استنادى
    -0.68
    NameInMap
    -0.64
    WithIOException
    -0.61
    Demografie
    -0.60
    oneofs
    -0.60
    Kariera
    -0.58
    saraba
    -0.58
    GEBURTSDATUM
    -0.57
    POSITIVE LOGITS
    šti
    0.51
    ruptedException
    0.49
     tearDown
    0.47
     trickle
    0.47
     loin
    0.46
    tanleria
    0.46
    thro
    0.45
    日閲覧
    0.44
     متعلقه
    0.44
     تكبرها
    0.43
    Activations Density 1.138%

    No Known Activations