© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12231
    Prev
    Next
    INDEX
    Explanations

    scientific research publications, including study designs, gene names, and citation references

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     zanahoria
    -0.45
     cruzar
    -0.41
     estekak
    -0.39
    াই
    -0.38
     menj
    -0.38
    InstanceState
    -0.36
     comunicarse
    -0.36
     hay
    -0.36
    justifyContent
    -0.36
    Trou
    -0.35
    POSITIVE LOGITS
     myſelf
    0.95
     himſelf
    0.91
     Jefus
    0.90
     itſelf
    0.87
     purpoſe
    0.86
     AssemblyTitle
    0.85
     Efq
    0.84
     оригіналу
    0.83
     tartalomajánló
    0.81
     themſelves
    0.80
    Activations Density 3.084%

    No Known Activations