© 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. 16329
    Prev
    Next
    INDEX
    Explanations

    states of being, especially the word "was", and the verb "to be".

    oai_token-act-pair · gemini-2.0-flash

    was

    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
    was
    -0.58
     was
    -0.54
    Was
    -0.49
     Was
    -0.47
    wasn
    -0.46
     Now
    -0.45
    ;
    -0.44
    now
    -0.44
    <eos>
    -0.44
    Now
    -0.43
    POSITIVE LOGITS
     Monfieur
    1.06
     Majefty
    1.04
    StoryboardSegue
    1.01
     Jefus
    0.98
     Efq
    0.97
    ^(@)
    0.95
    archiviato
    0.95
    elfare
    0.93
     myſelf
    0.91
     (\<
    0.85
    Activations Density 3.815%

    No Known Activations