© 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. 10473
    Prev
    Next
    INDEX
    Explanations

    content related to parenting and education, especially skills and abilities

    oai_token-act-pair · gemini-2.0-flash

    Skills

    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
    发表于
    -0.59
    BagLayout
    -0.54
     HasFactory
    -0.53
    แต่
    -0.53
    Scal
    -0.53
    étit
    -0.52
    дента
    -0.52
    makeText
    -0.52
    ContentAsync
    -0.52
    Varint
    -0.51
    POSITIVE LOGITS
    AsUp
    0.54
    횟
    0.52
    glBegin
    0.49
    FilterChain
    0.49
     spatial
    0.49
    ьаж
    0.48
    ThemeOverlay
    0.48
     problem
    0.48
    eqnarray
    0.47
    RepeatedField
    0.47
    Activations Density 1.406%

    No Known Activations