© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5318
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating comparison or contrast

    oai_token-act-pair · gemini-2.0-flash

    as well as, rather than

    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
    It
    -0.65
    at
    -0.64
    <eos>
    -0.59
    .
    -0.57
      
    -0.57
    not
    -0.57
    Not
    -0.56
    -
    -0.56
    it
    -0.55
    '
    -0.54
    POSITIVE LOGITS
     myſelf
    1.56
     Monfieur
    1.55
    StoryboardSegue
    1.49
     Efq
    1.46
     Normdatei
    1.45
    ніципалі
    1.44
     becauſe
    1.43
     whoſe
    1.37
     ſeveral
    1.36
     itſelf
    1.36
    Activations Density 15.795%

    No Known Activations