© 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. 10287
    Prev
    Next
    INDEX
    Explanations

    the word "break" or "breaking" as well as phrases containing it, such as "break up" and "break down".

    oai_token-act-pair · gemini-2.0-flash

    break

    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
    Negative Logits
     break
    -2.27
     Break
    -2.16
     breaking
    -2.16
    Break
    -2.11
     breaks
    -2.11
    break
    -2.08
     broke
    -2.08
     Breaking
    -1.95
     Breaks
    -1.94
     BREAK
    -1.90
    POSITIVE LOGITS
     orbit
    0.47
    المشاركات
    0.46
     kaban
    0.42
     affaire
    0.42
    Einsatz
    0.42
     traite
    0.41
    aspectj
    0.41
     Direito
    0.41
    machung
    0.41
     transpiration
    0.40
    Activations Density 1.291%

    No Known Activations