© 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. 10409
    Prev
    Next
    INDEX
    Explanations

    words and hyphenated words containing "up" with varied meanings, along with "line" and make".

    oai_token-act-pair · gemini-2.0-flash

    say "up" or "-"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cref
    -0.50
    qrstuvwxyz
    -0.50
    ∎
    -0.45
    ributions
    -0.45
    Altri
    -0.45
     in
    -0.42
    rami
    -0.41
    j
    -0.40
     N
    -0.40
     D
    -0.40
    POSITIVE LOGITS
     up
    2.28
     Up
    1.89
    Up
    1.88
    up
    1.86
     UP
    1.63
     ups
    1.54
    ups
    1.54
    UP
    1.53
    アップ
    1.48
     Ups
    1.33
    Activations Density 0.512%

    No Known Activations