© 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. 10081
    Prev
    Next
    INDEX
    Explanations

    words with diacritics like acute, grave, or tilde, especially from Hungarian language

    oai_token-act-pair · gemini-2.0-flash

    technical and foreign texts

    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
    complexType
    -0.61
    ApiModelProperty
    -0.59
    PostMapping
    -0.54
    didSet
    -0.50
    STRUCTIONS
    -0.49
    ofold
    -0.49
    RequestMapping
    -0.48
    SuspendLayout
    -0.48
     sum
    -0.46
    hime
    -0.46
    POSITIVE LOGITS
     beginnetje
    0.66
     CascadeType
    0.65
    providedIn
    0.64
    ImageContext
    0.62
    Personensuche
    0.61
    IndentedString
    0.61
    writeFieldEnd
    0.60
    OutputType
    0.58
     Mores
    0.58
     ComVisible
    0.57
    Activations Density 0.193%

    No Known Activations