© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12627
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    NUMX
    -0.67
    Naissance
    -0.62
     برانيه
    -0.61
    bigliamento
    -0.60
     الرياضيه
    -0.58
    <!--[
    -0.58
    Véxase
    -0.55
    nsito
    -0.54
     retrovisor
    -0.53
    grès
    -0.52
    POSITIVE LOGITS
     myſelf
    0.63
     Monfieur
    0.61
     APD
    0.59
     ſche
    0.58
     greateſt
    0.57
     pleaſure
    0.54
     εἰ
    0.53
     fhew
    0.53
    :✨
    0.52
     
    0.52
    Activations Density 6.167%

    No Known Activations