© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6892
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "instead," particularly when used to express contrast or a negative consequence.

    oai_token-act-pair · gemini-2.0-flash

    instead

    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
     instead
    -2.97
    instead
    -2.77
    Instead
    -2.56
     Instead
    -2.52
     rather
    -2.52
    rather
    -2.25
     Rather
    -2.20
    Rather
    -2.17
     plutôt
    -2.02
     invece
    -2.02
    POSITIVE LOGITS
    Viitteet
    0.65
    OGND
    0.64
    portál
    0.62
     насељу
    0.61
     beginnetje
    0.60
     disponibilités
    0.56
    SupportActionBar
    0.56
    Personensuche
    0.54
    TypedDataSet
    0.51
    Bibliograf
    0.50
    Activations Density 4.166%

    No Known Activations