© 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. 10315
    Prev
    Next
    INDEX
    Explanations

    US states and some related capitalized words such as the

    oai_token-act-pair · gemini-2.0-flash

    organizations and locations

    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
     too
    -0.80
    too
    -0.57
     TOO
    -0.54
    Too
    -0.52
     Too
    -0.51
     brid
    -0.44
     troppo
    -0.43
    BitmapFactory
    -0.43
     horny
    -0.43
     BitmapFactory
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.66
    Rüyada
    0.65
     täv
    0.62
     berätt
    0.62
     flesta
    0.60
     ljus
    0.57
     säs
    0.57
    FontOfSize
    0.57
     själva
    0.57
     autorytatywna
    0.57
    Activations Density 1.471%

    No Known Activations