© 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. 10175
    Prev
    Next
    INDEX
    Explanations

    code and file extensions

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
     iconFacebook
    -0.91
     Efq
    -0.90
     Jefus
    -0.84
     Monfieur
    -0.81
     purpoſe
    -0.80
    ſelves
    -0.79
    ."));
    -0.78
     Majefty
    -0.78
    neſs
    -0.78
    nefs
    -0.77
    POSITIVE LOGITS
    の
    0.68
     по
    0.68
     на
    0.66
     в
    0.66
    が
    0.65
     في
    0.63
     не
    0.63
    で
    0.62
     за
    0.62
    は
    0.61
    Activations Density 15.779%

    No Known Activations