© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16353
    Prev
    Next
    INDEX
    Explanations

    words that can be found in academic or scientific publications

    oai_token-act-pair · gemini-2.0-flash

    pos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Roskov
    -1.05
    tagHelperRunner
    -0.95
    transQ
    -0.90
    ఔ
    -0.86
     nakalista
    -0.84
     <",
    -0.84
     CURIAM
    -0.83
    verwijspagina
    -0.82
     صوتيه
    -0.82
    +#+#
    -0.80
    POSITIVE LOGITS
    éndolo
    0.47
    GraphicsUnit
    0.45
    multicolumn
    0.44
    getSub
    0.44
    씩
    0.43
     career
    0.43
    까지
    0.42
    intosh
    0.41
    enumi
    0.41
     &
    0.41
    Activations Density 27.959%

    No Known Activations