© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6215
    Prev
    Next
    INDEX
    Explanations

    words that are part of a list or series

    oai_token-act-pair · gemini-2.0-flash

    Random assorted text

    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
     test
    -1.09
     Test
    -1.00
     testing
    -0.95
    test
    -0.94
    ConstraintMaker
    -0.93
     TEST
    -0.91
     Testing
    -0.90
    TEST
    -0.87
     testers
    -0.85
    Test
    -0.85
    POSITIVE LOGITS
     pelas
    0.46
    เล
    0.46
     verw
    0.45
    zmir
    0.44
     poupée
    0.44
    Oc
    0.42
    oc
    0.42
     incendio
    0.42
     dzī
    0.42
     tör
    0.41
    Activations Density 2.192%

    No Known Activations