© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11006
    Prev
    Next
    INDEX
    Explanations

    escape characters for formatting text

    oai_token-act-pair · gemini-2.0-flash

    say "n"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     onCreateView
    -0.68
     للاسماء
    -0.68
    AddTagHelper
    -0.68
     Tartar
    -0.67
     vectorielle
    -0.66
     asiatique
    -0.65
    fromnode
    -0.65
     playmobil
    -0.65
    Vidite
    -0.62
     vectorielles
    -0.62
    POSITIVE LOGITS
     n
    0.78
    n
    0.71
    ny
    0.61
     r
    0.59
     N
    0.56
    r
    0.54
     t
    0.52
     U
    0.51
     Ro
    0.51
     thi
    0.49
    Activations Density 1.583%

    No Known Activations