© 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. 10271
    Prev
    Next
    INDEX
    Explanations

    numbers or percentage values

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash

    leading space Method used: 1 — because every max token starts with a leading space — leading space

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109

    ▁ 1 — begins with leading space — ▁

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
     initComponents
    -1.16
     ویکی‌پدیای
    -1.13
     سكانية
    -1.11
    BufferException
    -1.09
     itſelf
    -1.05
     Efq
    -1.04
     ویکی‌پدی
    -1.02
     Италијани
    -1.00
     tartalomajánló
    -1.00
     للاسماء
    -0.99
    POSITIVE LOGITS
    1
    0.84
     
    0.81
    3
    0.78
    2
    0.75
    5
    0.70
    4
    0.68
     III
    0.66
    6
    0.66
    7
    0.64
     II
    0.64
    Activations Density 26.412%

    No Known Activations