© 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. 4374
    Prev
    Next
    INDEX
    Explanations

    the word "took" or other past-tense forms of the verb "take"

    oai_token-act-pair · gemini-2.0-flash

    take

    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
     W
    -0.49
    K
    -0.47
     
    -0.47
     To
    -0.46
     K
    -0.46
     i
    -0.45
     j
    -0.44
     P
    -0.44
    enter
    -0.43
     (
    -0.43
    POSITIVE LOGITS
     Monfieur
    0.95
     myſelf
    0.93
     Efq
    0.84
     itſelf
    0.84
     Jefus
    0.83
     vectorstock
    0.79
     themſelves
    0.78
     himſelf
    0.77
     Theſe
    0.76
     fhew
    0.74
    Activations Density 0.604%

    No Known Activations