© 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. 3797
    Prev
    Next
    INDEX
    Explanations

    comments starting with "So" or "Okay".

    oai_token-act-pair · gemini-2.0-flash

    so

    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
    MeasureSpec
    -0.79
     unknownFields
    -0.75
    adaptiveStyles
    -0.73
     Futura
    -0.69
    iritto
    -0.68
    pread
    -0.67
    AllAfrica
    -0.66
     snippetHide
    -0.66
     tartalomajánló
    -0.66
    enoord
    -0.65
    POSITIVE LOGITS
    So
    0.72
     So
    0.72
    so
    0.54
     The
    0.50
    The
    0.50
     so
    0.49
     I
    0.48
     
    0.47
    SO
    0.46
     B
    0.46
    Activations Density 0.998%

    No Known Activations