© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15221
    Prev
    Next
    INDEX
    Explanations

    a wide range of text including dates, astronomy, shopping and math.

    oai_token-act-pair · gemini-2.0-flash

    non-English terms or foreign words

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    
    -0.68
     Roskov
    -0.64
     архивлан
    -0.63
     بيها
    -0.59
     kasarigan
    -0.58
    enumii
    -0.58
    Diwedd
    -0.57
    hans
    -0.53
    complexContent
    -0.52
    Personensuche
    -0.50
    POSITIVE LOGITS
    Viited
    0.62
     Turquie
    0.54
     NgModule
    0.53
     sumpay
    0.51
    rinol
    0.51
    DockStyle
    0.50
    φυ
    0.49
    ittäin
    0.48
    atriz
    0.47
     Cree
    0.47
    Activations Density 1.993%

    No Known Activations