© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    gibberish

    oai_token-act-pair · 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
    ChildScrollView
    -0.75
    UrlResolution
    -0.71
     CommonModule
    -0.61
    ruptedException
    -0.57
     memoized
    -0.57
    nastics
    -0.55
    ,:)
    -0.54
    extAlignment
    -0.54
    PhysRevD
    -0.54
     onCreateView
    -0.53
    POSITIVE LOGITS
    ceğim
    0.49
     houver
    0.47
     aikana
    0.47
     officiels
    0.46
     adhé
    0.46
    Литература
    0.46
     nég
    0.46
    ModelSerializer
    0.45
    dtd
    0.45
     monster
    0.44
    Activations Density 0.929%

    No Known Activations