© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10681
    Prev
    Next
    INDEX
    Explanations

    instances of the word "funny", and sometimes tags relating to comics or comic strips

    oai_token-act-pair · gemini-2.0-flash

    funny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     tartalomajánló
    -1.23
     engraçado
    -1.07
     سكانية
    -1.02
    HtmlAttribute
    -0.96
     hObject
    -0.95
    principalColumn
    -0.94
     BoxFit
    -0.94
     CommonModule
    -0.93
     Мексичка
    -0.92
    脚注の使い方
    -0.92
    POSITIVE LOGITS
    iry
    0.63
     Che
    0.58
    else
    0.57
    بول
    0.57
     Fo
    0.56
     Cha
    0.55
    New
    0.54
    iv
    0.54
    Su
    0.54
    Fe
    0.54
    Activations Density 0.905%

    No Known Activations