© 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. 15605
    Prev
    Next
    INDEX
    Explanations

    names and terms related to publishing, shipping, and business in general

    oai_token-act-pair · gemini-2.0-flash

    names

    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
     IndexPath
    -0.63
    netbeans
    -0.58
     lenker
    -0.58
    KEYCODE
    -0.57
     paramInt
    -0.57
    aternion
    -0.57
    diction
    -0.55
    glTexCoord
    -0.55
    WebServlet
    -0.54
    optarg
    -0.54
    POSITIVE LOGITS
    AnimationsModule
    0.67
     Roskov
    0.57
     actionMode
    0.55
    )}</
    0.55
    PropertyGroup
    0.50
     незавершена
    0.47
    titleMargin
    0.45
    BufferException
    0.45
    )$_
    0.44
    base
    0.43
    Activations Density 0.386%

    No Known Activations