© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13355
    Prev
    Next
    INDEX
    Explanations

    the existence of rules or laws, and their application in different contexts

    oai_token-act-pair · gemini-2.0-flash

    rules

    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
     BorderSide
    -0.76
    enderror
    -0.76
    AndEndTag
    -0.73
    twimg
    -0.69
     mergeFrom
    -0.66
    enumii
    -0.66
     EdgeInsets
    -0.66
    
    -0.60
    tvguidetime
    -0.60
    tilhe
    -0.60
    POSITIVE LOGITS
     agreed
    0.52
     stipulated
    0.51
     called
    0.50
    MLLoader
    0.49
    ObjectContext
    0.47
     applied
    0.47
     intended
    0.46
    Collegamenti
    0.45
    名は
    0.44
    verifier
    0.44
    Activations Density 8.001%

    No Known Activations