© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11267
    Prev
    Next
    INDEX
    Explanations

    US place names, often followed by a comma

    oai_token-act-pair · gemini-2.0-flash

    commas

    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
     disambiguazione
    -0.61
     pháp
    -0.55
     diff
    -0.54
    ReusableCell
    -0.53
     defaultstate
    -0.53
     Span
    -0.52
    crollView
    -0.50
     gal
    -0.50
     sp
    -0.50
    Fl
    -0.50
    POSITIVE LOGITS
     <=",
    0.60
    帖最后由
    0.57
    
    0.56
    GMENT
    0.54
    الدراسه
    0.54
    ométrique
    0.54
    articolo
    0.52
    ALTY
    0.52
    ignoire
    0.52
     Infórmanos
    0.51
    Activations Density 0.918%

    No Known Activations