© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10705
    Prev
    Next
    INDEX
    Explanations

    negative opinions on Marvel films and the discussion of diversity in them

    oai_token-act-pair · gemini-2.0-flash

    Marvel Cinematic Universe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ArrayAdapter
    -0.55
    invokeLater
    -0.50
     chré
    -0.47
     hâte
    -0.45
     виправивши
    -0.44
     régional
    -0.44
     comigo
    -0.43
     noastre
    -0.43
     Gaya
    -0.42
     iArr
    -0.42
    POSITIVE LOGITS
    
    0.72
     MCU
    0.61
     Pietro
    0.59
    })();
    0.57
     Maw
    0.57
    Assemble
    0.57
    %;">
    0.57
     Stark
    0.57
     snippetHide
    0.56
    日閲覧
    0.56
    Activations Density 0.529%

    No Known Activations