© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13187
    Prev
    Next
    INDEX
    Explanations

    words involved in plots involving heroes, villains, and battles within science fiction stories.

    oai_token-act-pair · gemini-2.0-flash

    Science fiction battles

    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
    Sadly
    -0.55
    Ibn
    -0.54
    lepiej
    -0.54
    latimes
    -0.53
     conmigo
    -0.53
     المعيارى
    -0.51
    ofsky
    -0.51
     Putra
    -0.51
     Causeway
    -0.50
     Sadly
    -0.50
    POSITIVE LOGITS
    ?
    
    0.66
    )");
    
    0.64
    [])
    
    0.62
    ")));
    
    0.61
     ]
    
    0.60
    __))
    0.60
    '):
    
    0.59
    ++
    
    0.59
    ')));
    0.58
    []
    
    0.58
    Activations Density 20.294%

    No Known Activations