© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7420
    Prev
    Next
    INDEX
    Explanations

    somewhat rare letter patterns, sometimes near the start of a word and sometimes near the end

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     مرئيه
    -0.67
     AppCompatTheme
    -0.65
    AMES
    -0.57
     intStringLen
    -0.57
    ьаж
    -0.56
     Mar
    -0.56
     يتيمه
    -0.55
     AssemblyProduct
    -0.55
     Италијани
    -0.55
    MAE
    -0.54
    POSITIVE LOGITS
    Miri
    0.71
    μισ
    0.66
    МИ
    0.66
    miu
    0.65
     mi
    0.64
    MIR
    0.64
     mii
    0.63
     mis
    0.63
     Mishra
    0.61
    ミ
    0.60
    Activations Density 1.960%

    No Known Activations