© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3819
    Prev
    Next
    INDEX
    Explanations

    the Roman numeral I

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    I
    -2.09
     I
    -2.06
    Ｉ
    -0.93
    我都
    -0.81
     i
    -0.80
     я
    -0.77
    ฉัน
    -0.69
    𝐼
    -0.68
    的我
    -0.67
     Ive
    -0.66
    POSITIVE LOGITS
    Personendaten
    0.74
    
    0.62
     autorytatywna
    0.62
    AutoScaleMode
    0.59
     nahilalakip
    0.59
    
    0.59
    FunctionFlags
    0.58
     mergeFrom
    0.57
    ErrUnexpectedEOF
    0.57
    riotic
    0.56
    Activations Density 1.064%

    No Known Activations