© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14239
    Prev
    Next
    INDEX
    Explanations

    situations or activities that have or could have a positive or negative outcome

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Personendaten
    -0.91
     vaccin
    -0.81
    Abitanti
    -0.77
     consec
    -0.74
     redraw
    -0.72
     Normdatei
    -0.71
     isolate
    -0.70
     uninstall
    -0.69
     impregn
    -0.69
    prefixer
    -0.69
    POSITIVE LOGITS
     tried
    0.69
     dealt
    0.61
     returned
    0.59
     pulled
    0.59
     explored
    0.57
     tended
    0.56
     attempted
    0.56
     celebrated
    0.56
     accepted
    0.56
     suggested
    0.55
    Activations Density 23.724%

    No Known Activations