© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9371
    Prev
    Next
    INDEX
    Explanations

    scandinavian language

    oai_token-act-pair · gemini-2.0-flash

    Danish/Norwegian movies and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -1.19
     purpoſe
    -1.16
    __":
    -1.13
     ſtate
    -1.08
    __':
    -1.06
     Houſe
    -1.05
     houſe
    -1.02
     pleaſure
    -1.02
    migrationBuilder
    -1.01
     reaſon
    -1.01
    POSITIVE LOGITS
     in
    0.74
    ,
    0.57
    er
    0.57
     run
    0.56
     pair
    0.53
    ;
    0.53
     
    0.52
     حالی
    0.52
    run
    0.52
     themselves
    0.52
    Activations Density 0.150%

    No Known Activations