© 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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1544
    Prev
    Next
    INDEX
    Explanations

    misspellings, especially flagged by the use of "[sic]" in the text

    oai_token-act-pair · gemini-2.0-flash

    spelling/misspellings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    StoryboardSegue
    -0.72
    BeginInit
    -0.65
    ագրություններ
    -0.63
     }}"></
    -0.56
    unnitel
    -0.55
    =$?
    -0.54
    Примітки
    -0.54
    henswürdigkeiten
    -0.54
     })
    
    -0.51
    ScopeManager
    -0.50
    POSITIVE LOGITS
    FORMAN
    0.60
     énergé
    0.55
    AddTagHelper
    0.55
    hésite
    0.54
     heller
    0.53
     onCancelled
    0.50
    opardy
    0.50
     Signalez
    0.49
     absolue
    0.48
    ]--;
    0.47
    Activations Density 0.748%

    No Known Activations