© 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. 14251
    Prev
    Next
    INDEX
    Explanations

    a mix of geographical terms and the abbreviation "reg" possibly for regression

    oai_token-act-pair · gemini-2.0-flash

    continent

    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
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.20
     myſelf
    -1.18
    ſelf
    -1.16
     houſe
    -1.14
     raiſ
    -1.13
     itſelf
    -1.13
     Efq
    -1.12
     himſelf
    -1.09
     pleaſure
    -1.09
     themſelves
    -1.09
    POSITIVE LOGITS
     esa
    0.71
    EndContext
    0.70
     ese
    0.66
     ist
    0.66
     acum
    0.65
    stdc
    0.65
     las
    0.65
    PageContext
    0.65
     zum
    0.64
     trận
    0.63
    Activations Density 2.219%

    No Known Activations