© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3091
    Prev
    Next
    INDEX
    Explanations

    second person pronouns and the verb "to be".

    oai_token-act-pair · gemini-2.0-flash

    if

    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
     he
    -0.46
     f
    -0.46
     am
    -0.45
     
    -0.43
     full
    -0.43
     line
    -0.43
     pi
    -0.43
     B
    -0.43
     so
    -0.43
     b
    -0.42
    POSITIVE LOGITS
     Monfieur
    1.00
     للمعارف
    0.94
     تانيه
    0.90
     Majefty
    0.84
     Efq
    0.82
     myſelf
    0.79
    IntoConstraints
    0.77
    RegressionTest
    0.76
     alſo
    0.75
     becauſe
    0.73
    Activations Density 2.661%

    No Known Activations