© 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. 14380
    Prev
    Next
    INDEX
    Explanations

    words about programs, events, and hosting

    oai_token-act-pair · gemini-2.0-flash

    hosted

    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
     devriez
    -0.57
    )}_
    -0.56
     voyons
    -0.52
     voyez
    -0.50
     []:
    -0.50
     végét
    -0.50
     devrez
    -0.49
    ?>
    -0.49
    =".
    -0.48
     dirait
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.88
    ngdoc
    0.83
    AddHtmlAttribute
    0.75
     showcasing
    0.75
    DockStyle
    0.73
    fjspx
    0.72
    omiast
    0.69
    ↵↵
    0.68
     actionTypes
    0.68
     الحره
    0.66
    Activations Density 1.748%

    No Known Activations