© 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. 4255
    Prev
    Next
    INDEX
    Explanations

    text written in a non-English language

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    np_max-act-logits · 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
     grève
    -0.66
     planète
    -0.59
     vallée
    -0.56
     vœux
    -0.54
     céramique
    -0.52
     vérit
    -0.52
     genoux
    -0.51
     fumée
    -0.50
     bénévoles
    -0.49
     connaissances
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.78
    BeginContext
    0.76
    aarrggbb
    0.75
    MemoryWarning
    0.73
    GraphicsUnit
    0.73
     createContext
    0.69
     BorderSide
    0.68
     StringTokenizer
    0.68
     Normdatei
    0.68
    dafx
    0.68
    Activations Density 0.235%

    No Known Activations