© 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. 1040
    Prev
    Next
    INDEX
    Explanations

    small words such as articles, prepositions, or conjunctions

    oai_token-act-pair · gemini-2.0-flash

    text snippets

    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
     Cæsar
    -0.79
     ―――――
    -0.75
     Anſ
    -0.73
     Patro
    -0.73
     Efq
    -0.70
     Theſe
    -0.70
     Monfieur
    -0.69
     Shakspeare
    -0.69
     Majefty
    -0.69
    ſelf
    -0.69
    POSITIVE LOGITS
     W
    0.58
     J
    0.57
     San
    0.57
     Bad
    0.52
     H
    0.52
     St
    0.51
     Vancouver
    0.51
    ಿಯ
    0.49
     Jersey
    0.49
     G
    0.48
    Activations Density 7.660%

    No Known Activations