© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8169
    Prev
    Next
    INDEX
    Explanations

    code or documentation that contains a return statement

    oai_token-act-pair · gemini-2.0-flash

    return

    np_max-act · gemini-2.0-flash
    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
     StatefulWidget
    -0.97
    GraphicsUnit
    -0.94
    ScopeManager
    -0.88
     InputDecoration
    -0.84
    providedIn
    -0.84
    StructEnd
    -0.83
     GenerationType
    -0.80
    Geplaatst
    -0.79
    HasAnnotation
    -0.76
    তথ্য
    -0.75
    POSITIVE LOGITS
     neither
    0.55
    ,
    0.49
                            
    0.49
    .
    0.49
     Neither
    0.48
    mtd
    0.48
     historical
    0.47
              
    0.47
    Neither
    0.46
    ither
    0.46
    Activations Density 0.372%

    No Known Activations