© 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. 12080
    Prev
    Next
    INDEX
    Explanations

    words indicating importance or relevance

    oai_token-act-pair · gemini-2.0-flash

    receive

    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
    tagHelperRunner
    -0.92
     cherchés
    -0.87
    تقاوى
    -0.81
    PreferredItem
    -0.79
     مشين
    -0.74
     '\\;'
    -0.73
    GenerationType
    -0.71
    SequentialGroup
    -0.70
    Revenir
    -0.69
     незавершена
    -0.68
    POSITIVE LOGITS
     receive
    1.98
     receiving
    1.88
     received
    1.85
     receives
    1.83
     Receiving
    1.66
     Receive
    1.64
    receive
    1.63
    receiving
    1.59
    received
    1.59
     recie
    1.56
    Activations Density 2.858%

    No Known Activations