© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8356
    Prev
    Next
    INDEX
    Explanations

    a broad group of words and phrases relating to medical/physical ailments or repairs.

    oai_token-act-pair · gemini-2.0-flash

    problems and technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Personendaten
    -0.93
    AndroidJUnit
    -0.76
    GEBURTS
    -0.75
    principalTable
    -0.71
    UnusedPrivate
    -0.71
    ArgumentParser
    -0.70
     ProtoMessage
    -0.70
     مشين
    -0.69
    httphttps
    -0.68
    RenderAtEndOf
    -0.68
    POSITIVE LOGITS
     juridiques
    0.40
     közül
    0.40
    allez
    0.39
    りに
    0.39
     above
    0.39
     commerciaux
    0.39
     missed
    0.38
    ioen
    0.38
     legales
    0.37
     Lucha
    0.37
    Activations Density 0.852%

    No Known Activations