© 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. 4449
    Prev
    Next
    INDEX
    Explanations

    words related to how the brain processes visual information

    oai_token-act-pair · gemini-2.0-flash

    neuron activity

    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
    stateProvider
    -0.54
     Billie
    -0.48
     للمعارف
    -0.47
     MatDialog
    -0.47
     Lights
    -0.46
    SqlSession
    -0.46
    WriteTagHelper
    -0.45
    Lights
    -0.45
    för
    -0.44
    cstdio
    -0.44
    POSITIVE LOGITS
    ьаж
    0.68
    OGND
    0.63
    sidemargin
    0.62
    PageIndex
    0.56
    ruptedException
    0.56
    Kjelder
    0.55
    urantes
    0.55
     initComponents
    0.53
    原始内容存档
    0.52
     Thar
    0.52
    Activations Density 2.845%

    No Known Activations