© 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. 12838
    Prev
    Next
    INDEX
    Explanations

    extremely specific production details for a 1971 Plymouth Hemi 'Cuda

    oai_token-act-pair · 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
    ReusableCell
    -0.81
     makeStyles
    -0.68
     ainfi
    -0.66
     المعيارى
    -0.65
     Decorating
    -0.63
     Dens
    -0.61
     spesa
    -0.59
     épis
    -0.58
     morire
    -0.58
     pouvoit
    -0.57
    POSITIVE LOGITS
    afficheront
    0.66
     Ser
    0.58
     Bon
    0.57
     Chi
    0.57
     Fire
    0.56
     Sund
    0.53
     St
    0.52
    haku
    0.52
     Side
    0.51
     Stone
    0.51
    Activations Density 1.791%

    No Known Activations