© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10707
    Prev
    Next
    INDEX
    Explanations

    code related to database connections

    oai_token-act-pair · gemini-2.0-flash

    Code and databases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     initComponents
    -0.71
     发表于
    -0.70
     BoxDecoration
    -0.66
    endphp
    -0.66
    XmlAccessType
    -0.66
     useContext
    -0.64
    Ligne
    -0.64
    CompleteListener
    -0.63
    cshtml
    -0.59
    éos
    -0.59
    POSITIVE LOGITS
     čer
    0.46
     Theſe
    0.46
    }))
    
    0.46
     vicenda
    0.43
    ysacchar
    0.42
     kud
    0.42
    évaluateur
    0.42
     quæ
    0.41
     Queste
    0.41
    fromLTRB
    0.41
    Activations Density 1.075%

    No Known Activations