© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13635
    Prev
    Next
    INDEX
    Explanations

    sentence fragments of various kinds across multiple unrelated topics

    oai_token-act-pair · gemini-2.0-flash

    Incomplete sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    kuuta
    -0.52
    hdys
    -0.52
    GeneratedCode
    -0.49
     success
    -0.47
     successfully
    -0.46
    djangoproject
    -0.45
     dit
    -0.45
     cut
    -0.44
     nô
    -0.44
    تفصیلات
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.63
    ViewFeatures
    0.60
     EconPapers
    0.58
    
    0.58
    awaiter
    0.54
     propOrder
    0.54
    archiviato
    0.54
    RetentionPolicy
    0.54
    errHandler
    0.52
    ])[
    0.52
    Activations Density 3.175%

    No Known Activations