© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9758
    Prev
    Next
    INDEX
    Explanations

    phrases or words that refer to things being disrupted or broken

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     break
    -3.13
     Break
    -3.05
     breaking
    -2.97
    break
    -2.95
    Break
    -2.94
     breaks
    -2.94
     broken
    -2.91
     broke
    -2.86
     BREAK
    -2.78
     Breaks
    -2.73
    POSITIVE LOGITS
    awtextra
    0.54
     ganda
    0.46
    ]]);
    0.46
    󠁢
    0.45
     acepción
    0.42
    OptionsMenu
    0.42
     (*.
    0.41
    OTS
    0.41
    atterns
    0.41
    цы
    0.41
    Activations Density 1.954%

    No Known Activations