© 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. 12785
    Prev
    Next
    INDEX
    Explanations

    a combination of strong opinions, especially negative ones, and references to time or numbers

    oai_token-act-pair · gemini-2.0-flash

    RIGHT

    np_max-act-logits · 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
     Aspect
    -0.73
     Part
    -0.73
     Place
    -0.71
     Stage
    -0.68
     Form
    -0.62
     Slice
    -0.61
     Ever
    -0.60
     Song
    -0.60
     Acre
    -0.60
    Part
    -0.59
    POSITIVE LOGITS
     Roskov
    0.81
     kasarigan
    0.79
    WriteTagHelper
    0.71
     مشين
    0.71
     незавершена
    0.71
    Personendaten
    0.66
    LabelTagHelper
    0.66
     useRouter
    0.63
     Humanos
    0.62
    Main
    0.61
    Activations Density 10.368%

    No Known Activations