© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15051
    Prev
    Next
    INDEX
    Explanations

    the word "whom", and only activates slightly for words associated with negativity or storytelling

    oai_token-act-pair · gemini-2.0-flash

    whom

    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
     Monfieur
    -1.62
     Theſe
    -1.52
     Reſ
    -1.47
     Efq
    -1.46
     itſelf
    -1.42
     Anſ
    -1.37
     Diſ
    -1.34
     themſelves
    -1.34
     myſelf
    -1.34
     Shakspeare
    -1.30
    POSITIVE LOGITS
     I
    0.86
     a
    0.83
     in
    0.78
     el
    0.78
     it
    0.75
     the
    0.74
     al
    0.71
    tillon
    0.70
     A
    0.70
     la
    0.69
    Activations Density 1.967%

    No Known Activations