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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5906
    Prev
    Next
    INDEX
    Explanations

    code blocks with bracketed expressions

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    ніципа
    -0.60
    Související
    -0.56
    cstdlib
    -0.53
    يكب
    -0.51
     Direct
    -0.51
     cap
    -0.51
     урна
    -0.49
    >[]
    -0.49
    ัท
    -0.49
    TestingModule
    -0.48
    POSITIVE LOGITS
                    
    0.55
    六
    0.52
     HasFactory
    0.51
     Bourgoin
    0.50
    prech
    0.49
     Sieger
    0.48
                  
    0.48
     六
    0.47
     dali
    0.47
                 
    0.47
    Activations Density 1.677%

    No Known Activations