© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15621
    Prev
    Next
    INDEX
    Explanations

    instances of sentences containing negative words such as "no" and "not"

    oai_token-act-pair · gemini-2.0-flash

    negations and strong affirmations

    np_token-act-pair-logits · gpt-4o-mini

    No

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bulat
    -0.53
     quaisquer
    -0.50
     dowol
    -0.48
     orice
    -0.48
    yttö
    -0.47
     juridiques
    -0.47
     todėl
    -0.46
     Normdatei
    -0.46
     devoirs
    -0.46
     généraux
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    1.01
    providedIn
    0.81
    WebServlet
    0.75
    EndInit
    0.71
     matter
    0.67
    قایناق‌لار
    0.64
    Datuak
    0.62
     للمعارف
    0.61
     Chwiliwch
    0.61
    sizeCache
    0.60
    Activations Density 0.650%

    No Known Activations