© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9526
    Prev
    Next
    INDEX
    Explanations

    mentions of ratios and proportions with related math symbols in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    ratio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Ratio
    -1.13
     ratio
    -1.09
    Ratio
    -1.03
     ratios
    -1.02
     RATIO
    -0.99
    ratio
    -0.98
     Ratios
    -0.94
    RATIO
    -0.90
    ratios
    -0.87
    SourceChecksum
    -0.83
    POSITIVE LOGITS
    izações
    0.58
     Efq
    0.57
     Anſ
    0.54
     miſ
    0.54
     ſtate
    0.52
     raiſ
    0.52
     vícti
    0.52
     Потому
    0.52
     ſtre
    0.52
     Majefty
    0.52
    Activations Density 14.874%

    No Known Activations