© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16315
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb or being used with a word like "help" or "just."

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Regardless
    -0.63
     jegy
    -0.58
    Regardless
    -0.58
     aren
    -0.57
     preventative
    -0.56
    имущества
    -0.55
    semantics
    -0.54
     llevará
    -0.54
     backstory
    -0.54
    Elsewhere
    -0.52
    POSITIVE LOGITS
     equipments
    0.66
    InstrumentedTest
    0.65
    #
    0.64
    ברס
    0.63
    ]")]
    0.63
    GMENT
    0.61
    __':
    0.60
     läßt
    0.59
    "]);
    0.59
    thâu
    0.58
    Activations Density 5.947%

    No Known Activations