© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11566
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be identifying research and medical findings and conclusions.

    oai_token-act-pair · gemini-2.0-flash

    Suggestion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     représ
    -0.58
    MeasureSpec
    -0.57
     VIAF
    -0.57
    CloseOperation
    -0.53
    GraphicsUnit
    -0.52
     ratón
    -0.47
     InputDecoration
    -0.46
     extérieures
    -0.46
    igshid
    -0.46
    setCellValue
    -0.45
    POSITIVE LOGITS
     suggests
    1.14
     suggest
    1.07
     sugiere
    1.02
    sugges
    1.00
     suggesting
    1.00
     Sugges
    0.96
    Sugges
    0.92
    suggest
    0.92
     Suggest
    0.91
     sugg
    0.86
    Activations Density 4.860%

    No Known Activations