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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10313
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe how things are said or done

    oai_token-act-pair · gemini-2.0-flash

    say "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_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
     correctly
    -1.18
     properly
    -1.11
     intelligently
    -1.07
     sensibly
    -1.06
    properly
    -1.04
     extensively
    -1.02
     brilliantly
    -1.02
     wisely
    -1.02
     cleverly
    -1.02
     smartly
    -0.99
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.71
    ly
    0.68
    ⓧ
    0.61
     vecchi
    0.52
     Référence
    0.47
    lytic
    0.47
     offerts
    0.45
     dobré
    0.45
    GTCX
    0.44
    posedge
    0.44
    Activations Density 2.591%

    No Known Activations