© 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. 3433
    Prev
    Next
    INDEX
    Explanations

    bibliographic or copyright information, including numbers, initials, and punctuation in a particular style

    oai_token-act-pair · gemini-2.0-flash

    page number

    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
     démocr
    -0.73
     sanitaires
    -0.68
     nationaux
    -0.67
     réguli
    -0.65
     étoient
    -0.65
     étoit
    -0.61
     avoient
    -0.61
     auroit
    -0.60
     umana
    -0.60
     détru
    -0.60
    POSITIVE LOGITS
    MENAFN
    0.76
     
    0.65
     
    0.64
     
    0.62
    `
    
    0.61
    '))
    
    0.60
     
    0.60
     }}
    0.59
    "))
    
    0.59
     }
    
    0.58
    Activations Density 15.159%

    No Known Activations