© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14745
    Prev
    Next
    INDEX
    Explanations

    words that are verbs in Spanish and Portuguese

    oai_token-act-pair · gemini-2.0-flash

    Mixed language code

    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
     he
    -1.10
     she
    -1.07
     them
    -0.94
     they
    -0.85
     we
    -0.79
     ellas
    -0.78
     ellos
    -0.77
    She
    -0.76
    He
    -0.71
     mình
    -0.71
    POSITIVE LOGITS
     его
    0.82
     його
    0.79
     их
    0.69
     їх
    0.68
     її
    0.61
    GOTREF
    0.58
    sua
    0.57
     jį
    0.57
     hans
    0.56
    his
    0.54
    Activations Density 0.298%

    No Known Activations