© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8344
    Prev
    Next
    INDEX
    Explanations

    code snippets or segments containing operators and variables

    oai_token-act-pair · gemini-2.0-flash

    code instructions

    np_max-act · gemini-2.0-flash

    say "suffixes" Method used: 2 — because following tokens are common word endings — say "suffixes"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     particulières
    -0.70
     cohé
    -0.70
     feroit
    -0.67
     craindre
    -0.67
     beginnetje
    -0.67
     fermés
    -0.66
     destinées
    -0.66
     rafraî
    -0.65
     wikipagina
    -0.65
     immédi
    -0.65
    POSITIVE LOGITS
    kenny
    0.68
    )}
    
    0.66
    VIEWS
    0.66
    }))
    
    0.65
     Mawr
    0.64
     gra
    0.63
    "],
    
    0.63
    aarrggbb
    0.63
     })
    
    0.62
    úly
    0.61
    Activations Density 0.196%

    No Known Activations