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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4926
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives ending in "-ly", "-ic", "-id", and "-ent"

    oai_token-act-pair · gemini-2.0-flash

    adverbs ending in 'ly'

    np_token-act-pair-logits · gpt-4o-mini

    say "the ending -ly"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    visející
    -0.52
    KURZBESCHREIBUNG
    -0.52
     sociala
    -0.49
     meilleurs
    -0.48
     meilleures
    -0.46
     mathématiques
    -0.46
     relatifs
    -0.46
     considérons
    -0.46
     professionali
    -0.45
     anteriore
    -0.43
    POSITIVE LOGITS
    ally
    1.84
    ALLY
    1.58
    ly
    1.52
    ably
    1.45
    antly
    1.44
    ously
    1.44
    ingly
    1.41
    ically
    1.39
    matically
    1.38
    ually
    1.36
    Activations Density 1.765%

    No Known Activations