© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6127
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word 'too' in the context of limitations or excess

    oai_token-act-pair · gemini-2.0-flash

    too

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     ModelExpression
    -0.79
     scolaires
    -0.67
    SpringBootTest
    -0.66
     ISTAT
    -0.61
    ributor
    -0.61
     priorité
    -0.60
    antart
    -0.58
    addCriterion
    -0.58
    anskje
    -0.58
    FTFY
    -0.57
    POSITIVE LOGITS
     too
    1.05
    Too
    1.02
     Too
    0.97
    too
    0.96
     TOO
    0.90
    TOO
    0.80
     demasi
    0.79
     troppo
    0.70
    太
    0.69
     terlalu
    0.69
    Activations Density 1.505%

    No Known Activations