© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12383
    Prev
    Next
    INDEX
    Explanations

    words that indicate the need to take action to obtain something

    oai_token-act-pair · gemini-2.0-flash

    get

    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
    oneofs
    -0.59
    ImageContext
    -0.59
     חיצוניים
    -0.56
    TacToe
    -0.53
     alimentaires
    -0.52
    Hentet
    -0.51
    patine
    -0.51
    aternary
    -0.48
    IsMutable
    -0.48
    carousel
    -0.47
    POSITIVE LOGITS
    endphp
    0.62
     estimés
    0.58
    pertise
    0.54
    PEACE
    0.52
     CreateTagHelper
    0.52
     ervan
    0.52
    شاركة
    0.52
     Segurança
    0.51
    omencl
    0.50
    strconv
    0.50
    Activations Density 0.545%

    No Known Activations