© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 797
    Prev
    Next
    INDEX
    Explanations

    danish names and words as well as years

    oai_token-act-pair · gemini-2.0-flash

    Scandinavia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     IBOutlet
    -0.59
    thâu
    -0.59
    setVerticalGroup
    -0.57
    Ĝ
    -0.56
     '\\;'
    -0.54
     فريبيس
    -0.53
    posedge
    -0.53
     noqa
    -0.52
    latego
    -0.52
    JsonPropertyName
    -0.51
    POSITIVE LOGITS
    脚注の使い方
    0.69
    Geplaatst
    0.60
     onStart
    0.52
     Meksiku
    0.50
     CURLOPT
    0.49
    gha
    0.49
    ftra
    0.49
     sko
    0.49
     cascada
    0.49
     pinulongan
    0.47
    Activations Density 1.413%

    No Known Activations