© 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. 10247
    Prev
    Next
    INDEX
    Explanations

    the word "can" and related auxiliary verbs like "will", "should", and "to"

    oai_token-act-pair · gemini-2.0-flash

    buying and sampling goods

    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
     vétérina
    -0.58
     refusé
    -0.56
     rayures
    -0.55
     accepté
    -0.54
     avancé
    -0.54
     magnético
    -0.54
     méri
    -0.53
     soeur
    -0.52
     autorités
    -0.51
     ordres
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.82
    Personendaten
    0.72
    hoeddwyd
    0.63
    
    0.63
    ագրություններ
    0.62
    AddHtmlAttribute
    0.60
     LUMP
    0.59
    setVerticalGroup
    0.58
     score
    0.58
    Personensuche
    0.58
    Activations Density 1.096%

    No Known Activations