© 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. 14268
    Prev
    Next
    INDEX
    Explanations

    words related to people or figures being directly quoted

    oai_token-act-pair · gemini-2.0-flash

    Historical recollections

    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
     ostavi
    -0.59
    bootstrapcdn
    -0.51
    Personendaten
    -0.50
    Външни
    -0.50
     postIndex
    -0.50
     complètes
    -0.48
     Meksiku
    -0.47
    Erreferentziak
    -0.46
    XmlAccessType
    -0.45
     msglen
    -0.45
    POSITIVE LOGITS
     myſelf
    0.66
    ")));
    0.60
     ―――――
    0.56
    diman
    0.54
     itſelf
    0.53
    ſelves
    0.52
     ſta
    0.52
     Monfieur
    0.52
    DataSetChanged
    0.52
    giu
    0.51
    Activations Density 2.615%

    No Known Activations