© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3867
    Prev
    Next
    INDEX
    Explanations

    sentences describing things that are done on a regular basis or are widely known

    oai_token-act-pair · gemini-2.0-flash

    common

    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
    Negative Logits
     T
    -0.51
     common
    -0.47
     typical
    -0.46
     usual
    -0.45
     commonly
    -0.44
     usually
    -0.43
     typically
    -0.42
     '
    -0.42
     Commonly
    -0.41
     her
    -0.41
    POSITIVE LOGITS
     Jefus
    0.96
     faſt
    0.95
     myſelf
    0.94
     Theſe
    0.94
     purpoſe
    0.91
     }}"></
    0.91
     Monfieur
    0.90
     Efq
    0.88
     itſelf
    0.87
     himſelf
    0.84
    Activations Density 4.776%

    No Known Activations