© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4515
    Prev
    Next
    INDEX
    Explanations

    scientific writing with statistical analysis of data collected from nature or a lab

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     iNdEx
    -0.58
    AccessException
    -0.53
     reveal
    -0.52
    reveal
    -0.52
    yser
    -0.51
     visualiser
    -0.51
     revealed
    -0.50
     onAnimation
    -0.50
    AutoField
    -0.50
    BUN
    -0.49
    POSITIVE LOGITS
    WebElementEntity
    0.64
     incomplete
    0.64
     coverage
    0.63
    GEBURTSDATUM
    0.61
     complete
    0.61
    principalTable
    0.61
    المكان
    0.61
     COMPLETE
    0.59
    Personensuche
    0.56
    Comple
    0.55
    Activations Density 5.844%

    No Known Activations