© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7213
    Prev
    Next
    INDEX
    Explanations

    Ruby code

    oai_token-act-pair · gemini-2.0-flash

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     withal
    -0.56
    StrictEqual
    -0.53
    
    -0.52
     reversal
    -0.50
     Spal
    -0.49
    streak
    -0.49
     rosette
    -0.49
     `.
    -0.49
     ་་
    -0.48
     gdyby
    -0.48
    POSITIVE LOGITS
    Autoritní
    0.77
    expandindo
    0.62
     beginnetje
    0.59
    GenerationType
    0.54
     End
    0.53
    Aholisi
    0.51
    الحياه
    0.50
    writeFieldEnd
    0.49
    Ending
    0.49
     kaarangay
    0.48
    Activations Density 1.378%

    No Known Activations