© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13874
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related discussions, especially those involving "si" conditional statements

    oai_token-act-pair · gemini-2.0-flash

    si

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     si
    -2.16
     Si
    -1.63
    Si
    -1.48
     SI
    -0.86
     bien
    -0.77
     se
    -0.64
     siphon
    -0.60
    Sip
    -0.59
     sip
    -0.59
     ni
    -0.57
    POSITIVE LOGITS
    RepeatedField
    0.74
    LEncoder
    0.73
    Gön
    0.72
     صوتيه
    0.72
     يتيمه
    0.70
     ModelRenderer
    0.68
     protoimpl
    0.68
    ISupport
    0.66
    ValueGeneration
    0.66
    tagHelperRunner
    0.66
    Activations Density 1.463%

    No Known Activations