© 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. 10423
    Prev
    Next
    INDEX
    Explanations

    the fragment "me" but it often misses, so I am not sure if this is the main thing!

    oai_token-act-pair · 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
     blessés
    -0.64
    存于互联网档案馆
    -0.64
    Gweler
    -0.61
    Bản
    -0.61
    Rujuakan
    -0.60
    httphttps
    -0.59
    ek
    -0.58
    脚注の使い方
    -0.57
     Référence
    -0.56
     malades
    -0.56
    POSITIVE LOGITS
     Autorisations
    0.45
    TRIBUT
    0.43
    NewUrlParser
    0.42
     okuyayım
    0.41
    paginator
    0.41
    GraphicsUnit
    0.41
     ContentValues
    0.41
     SEQUENCE
    0.41
    uxxxx
    0.41
    dai
    0.41
    Activations Density 1.718%

    No Known Activations