© 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. 15423
    Prev
    Next
    INDEX
    Explanations

    words related to academic associations and research networks

    oai_token-act-pair · gemini-2.0-flash

    committees and tasks

    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
    weit
    -0.45
    ismet
    -0.44
     quiver
    -0.43
     daly
    -0.42
    indere
    -0.42
    inalg
    -0.41
     crossorigin
    -0.41
    parseFrom
    -0.41
    ModelSerializer
    -0.41
     gustado
    -0.40
    POSITIVE LOGITS
     Working
    1.73
     working
    1.71
    Working
    1.57
     WORKING
    1.54
    working
    1.53
    WORKING
    1.46
     task
    1.34
     Task
    1.26
    task
    1.18
     Arbeits
    1.12
    Activations Density 2.094%

    No Known Activations