© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15596
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to availability and accessibility

    oai_token-act-pair · gemini-2.0-flash

    accessible

    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
    Negative Logits
     textStatus
    -0.83
     jScrollPane
    -0.82
    SequentialGroup
    -0.81
    adpleegd
    -0.73
    ituary
    -0.72
     esternos
    -0.71
     estekak
    -0.69
     nahilalakip
    -0.67
    ThroughAttribute
    -0.67
     EconPapers
    -0.66
    POSITIVE LOGITS
    ark
    0.48
     Verenig
    0.46
     Kartoff
    0.40
    BASEPATH
    0.39
    亿元
    0.39
    GetChild
    0.38
     menang
    0.38
    of
    0.38
    ASSOCI
    0.37
    瘙
    0.37
    Activations Density 1.423%

    No Known Activations