© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    Spanish words related to programming, code, and logic

    oai_token-act-pair · gemini-2.0-flash

    non-English "you"

    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
     your
    -0.90
     ва
    -0.82
     yours
    -0.74
     sizin
    -0.67
     votre
    -0.66
     iyong
    -0.65
     yako
    -0.65
     Ва
    -0.63
    yours
    -0.63
    Your
    -0.62
    POSITIVE LOGITS
     ihr
    0.88
    their
    0.82
     his
    0.75
     ihre
    0.72
    his
    0.72
     their
    0.72
     jego
    0.71
     her
    0.70
     its
    0.70
    ihr
    0.70
    Activations Density 0.629%

    No Known Activations