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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12308
    Prev
    Next
    INDEX
    Explanations

    mentions of availability and quantity

    oai_token-act-pair · gemini-2.0-flash

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Zunanje
    -0.56
    başı
    -0.52
    aarrggbb
    -0.52
     kív
    -0.51
    存于互联网档案馆
    -0.50
     brancas
    -0.48
    enterOuterAlt
    -0.48
     للمعارف
    -0.47
     bénévoles
    -0.47
     esenciales
    -0.47
    POSITIVE LOGITS
    findpost
    0.75
     CreateTagHelper
    0.63
     no
    0.59
    Personendaten
    0.59
    "):
    0.58
     ✭✭
    0.56
     Chwiliwch
    0.55
    +][
    0.54
    '):
    0.53
     {},
    0.53
    Activations Density 0.349%

    No Known Activations