© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5021
    Prev
    Next
    INDEX
    Explanations

    language related to project proposals

    oai_token-act-pair · gemini-2.0-flash

    Project

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Audiodateien
    -0.54
    EndTag
    -0.50
    audiovisuel
    -0.50
     useRef
    -0.49
    IContainer
    -0.48
    SequentialGroup
    -0.48
     chi̍t
    -0.47
    IBOutlet
    -0.46
     GlobalKey
    -0.45
     JADX
    -0.45
    POSITIVE LOGITS
    ']))
    0.63
    poons
    0.55
     CreateTagHelper
    0.54
    chọn
    0.54
    binom
    0.54
     désigner
    0.54
    gout
    0.54
    mities
    0.53
    ligheten
    0.52
    slant
    0.51
    Activations Density 25.023%

    No Known Activations