© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13237
    Prev
    Next
    INDEX
    Explanations

    words indicating a distinction between two things

    oai_token-act-pair · gemini-2.0-flash

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     and
    -0.57
    ag
    -0.54
     in
    -0.53
    l
    -0.52
     or
    -0.52
     at
    -0.49
    ax
    -0.49
     from
    -0.48
     braccia
    -0.47
    ’
    -0.47
    POSITIVE LOGITS
     Monfieur
    1.12
     Taktlose
    1.08
    tagHelperRunner
    1.05
     Signalez
    1.00
     myſelf
    0.99
     snippetHide
    0.97
    تقاوى
    0.96
    AddTagHelper
    0.95
     purpoſe
    0.95
     Efq
    0.94
    Activations Density 0.727%

    No Known Activations