© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14983
    Prev
    Next
    INDEX
    Explanations

    proper nouns and associated titles or descriptions

    oai_token-act-pair · gemini-2.0-flash

    Sentence structure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     former
    -2.97
     Former
    -2.80
    Former
    -2.77
    former
    -2.63
     ehemaligen
    -1.77
     formerly
    -1.73
     býval
    -1.72
     ehemalige
    -1.71
     Formerly
    -1.70
     mantan
    -1.66
    POSITIVE LOGITS
    ISupport
    0.54
     Signalez
    0.49
    RenderAtEndOf
    0.48
    着
    0.44
    ائص
    0.43
     CURLOPT
    0.42
     StatefulWidget
    0.42
    Erreferentziak
    0.42
    гӀ
    0.41
    ایان
    0.41
    Activations Density 2.356%

    No Known Activations