© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2375
    Prev
    Next
    INDEX
    Explanations

    memory addresses and system architecture concepts

    oai_token-act-pair · gemini-2.0-flash

    computer memory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     الرياضيه
    -0.66
     ModelExpression
    -0.65
    AndEndTag
    -0.61
    TestTools
    -0.59
    featureID
    -0.58
    DeleteBehavior
    -0.58
    SerializeField
    -0.57
     genoux
    -0.56
    WebServlet
    -0.55
     MatDialog
    -0.54
    POSITIVE LOGITS
    httphttps
    0.64
     anonymous
    0.53
    ArrowToggle
    0.48
     RW
    0.48
     Anonymous
    0.47
    mied
    0.47
     atlas
    0.47
     Rech
    0.47
    fils
    0.47
    mover
    0.46
    Activations Density 11.457%

    No Known Activations