© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10421
    Prev
    Next
    INDEX
    Explanations

    instances of the word "can" or "could."

    oai_token-act-pair · gemini-2.0-flash

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    couldn
    -0.91
     couldn
    -0.88
     Couldn
    -0.82
     EconPapers
    -0.81
     Cannot
    -0.81
     cant
    -0.77
     inability
    -0.76
    StoryboardSegue
    -0.76
    cannot
    -0.76
    ِّف
    -0.75
    POSITIVE LOGITS
     not
    1.78
    not
    1.30
     не
    1.13
     nicht
    1.07
    Not
    1.04
     ikke
    1.01
     niet
    1.00
     Not
    0.99
     não
    0.97
     NOT
    0.97
    Activations Density 2.147%

    No Known Activations