© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6853
    Prev
    Next
    INDEX
    Explanations

    intensifying words and phrases and personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    say "well"

    np_max-act-logits · gemini-2.0-flash

    say "well" Method used: 2 — because the following tokens are predominantly "well"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    WELL
    -0.75
    Well
    -0.68
    well
    -0.68
    ValueStyle
    -0.65
     Well
    -0.65
     Properly
    -0.59
    correctly
    -0.58
     WELL
    -0.57
    LOWER
    -0.55
    Fully
    -0.54
    POSITIVE LOGITS
     very
    1.27
     extremely
    1.21
    extremely
    1.05
    very
    1.02
     VERY
    0.99
     exceedingly
    0.98
     exceptionally
    0.96
     extraordinarily
    0.96
     très
    0.94
     muy
    0.93
    Activations Density 1.354%

    No Known Activations