© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14588
    Prev
    Next
    INDEX
    Explanations

    mentions of the words "twin," "cheap," and "best" in product reviews

    oai_token-act-pair · gemini-2.0-flash

    Twins or low cost

    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
     \\
    -0.68
     himſelf
    -0.67
     ';
    -0.66
    */;
    -0.66
     "];
    -0.66
     ').
    -0.65
     ')
    -0.65
     myſelf
    -0.65
     structure
    -0.62
     welches
    -0.62
    POSITIVE LOGITS
    principalColumn
    1.00
    GEBURTSDATUM
    0.85
     Савезне
    0.78
     NSCoder
    0.75
    windowFixed
    0.72
     Signalez
    0.71
    Enjoying
    0.70
     chré
    0.69
     Infórmanos
    0.69
     StatelessWidget
    0.69
    Activations Density 2.943%

    No Known Activations