© 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. 10371
    Prev
    Next
    INDEX
    Explanations

    years in the 1900s

    oai_token-act-pair · gemini-2.0-flash

    9

    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
     calendriers
    -0.85
    Diwedd
    -0.82
     feroit
    -0.80
     createContext
    -0.80
    ValueStyle
    -0.79
    AndEndTag
    -0.77
     تضيفلها
    -0.76
     auroit
    -0.75
    HasAnnotation
    -0.74
     <=",
    -0.74
    POSITIVE LOGITS
    7
    0.50
    6
    0.46
    8
    0.45
    ily
    0.44
    e
    0.44
     It
    0.44
    4
    0.43
    9
    0.42
    ф
    0.41
    ro
    0.41
    Activations Density 0.765%

    No Known Activations