© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10135
    Prev
    Next
    INDEX
    Explanations

    positive adjectives used to describe a book or blog

    oai_token-act-pair · gemini-2.0-flash

    down

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ENV
    -0.45
    走在
    -0.42
    Env
    -0.41
    ξύ
    -0.41
     feu
    -0.40
     morphine
    -0.39
     yêu
    -0.39
     intra
    -0.39
    ख्य
    -0.38
     feux
    -0.37
    POSITIVE LOGITS
     down
    1.26
    down
    1.07
     Down
    1.02
    Down
    1.01
     DOWN
    1.00
    AndEndTag
    0.99
    DOWN
    0.89
    downs
    0.88
    RegistryLite
    0.83
    ftagPool
    0.80
    Activations Density 2.146%

    No Known Activations