© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3481
    Prev
    Next
    INDEX
    Explanations

    what appears to be machine-translated text containing political and violent themes

    oai_token-act-pair · gemini-2.0-flash

    say "the" or "t" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     whereof
    -0.71
     itſelf
    -0.68
     Lyt
    -0.67
     SKS
    -0.65
    ждую
    -0.64
     ziren
    -0.64
     uska
    -0.63
     Selecciona
    -0.62
    Rujuakan
    -0.62
     Octo
    -0.61
    POSITIVE LOGITS
     the
    0.76
     bricolaje
    0.51
    abella
    0.46
    ison
    0.45
     human
    0.44
    saraba
    0.44
     #
    0.44
     it
    0.43
    ائب
    0.43
    omin
    0.41
    Activations Density 3.225%

    No Known Activations