© 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. 10395
    Prev
    Next
    INDEX
    Explanations

    the phrase "take a" or similar constructs ("took a", "taking a")

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    tanleria
    -0.94
     '\\;'
    -0.88
     <>",
    -0.81
    <?
    -0.77
     gynhyrchwyd
    -0.74
    mergeFrom
    -0.73
    endphp
    -0.72
     BoxFit
    -0.71
     nahilalakip
    -0.71
    Билгалдахарш
    -0.70
    POSITIVE LOGITS
     pag
    0.52
    ọa
    0.50
     Pag
    0.46
     gam
    0.46
    kund
    0.46
     risks
    0.44
     crack
    0.42
     Jackson
    0.42
    marital
    0.42
     risk
    0.41
    Activations Density 0.905%

    No Known Activations