© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14323
    Prev
    Next
    INDEX
    Explanations

    code file extensions and version numbers

    oai_token-act-pair · gemini-2.0-flash

    code files

    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
    
    -0.98
     resourceCulture
    -0.87
     فريبيس
    -0.83
    Datuak
    -0.77
    writeFieldEnd
    -0.74
     дописавши
    -0.73
    ReusableCell
    -0.73
    GraphicsUnit
    -0.71
     BoxFit
    -0.69
     Italijanski
    -0.68
    POSITIVE LOGITS
    琴
    0.45
     cuantas
    0.45
    cipl
    0.43
    ↵↵
    0.41
    "(
    0.41
    viste
    0.41
     eius
    0.41
    ?
    0.40
    ",
    0.40
    сах
    0.40
    Activations Density 2.867%

    No Known Activations