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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13432
    Prev
    Next
    INDEX
    Explanations

    the word "format" and variations of it

    oai_token-act-pair · gemini-2.0-flash

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     format
    -1.12
     formats
    -0.97
     Format
    -0.89
     FORMAT
    -0.75
     formato
    -0.74
     Formats
    -0.70
     formatos
    -0.65
    格式
    -0.59
    Format
    -0.56
    format
    -0.55
    POSITIVE LOGITS
     المعيارى
    0.98
     оригіналу
    0.92
    aarrggbb
    0.82
    تقاوى
    0.81
     كومونز
    0.79
    ellschaft
    0.79
     Мексичка
    0.78
    StoryboardSegue
    0.78
    PreferredItem
    0.77
    windowFixed
    0.77
    Activations Density 0.613%

    No Known Activations