© 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. 12713
    Prev
    Next
    INDEX
    Explanations

    proper nouns, labels, and location descriptions, particularly of organizations

    oai_token-act-pair · gemini-2.0-flash

    foreign conjunctions

    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
     et
    -0.75
     i
    -0.69
    Et
    -0.58
     compagni
    -0.56
     pensieri
    -0.53
     marito
    -0.53
     innamor
    -0.53
     ит
    -0.52
    슷
    -0.52
     ongles
    -0.52
    POSITIVE LOGITS
     ja
    1.51
     og
    1.17
     och
    1.14
     és
    1.00
     ve
    0.84
    Og
    0.82
     Och
    0.81
     Og
    0.79
    Och
    0.76
     OG
    0.68
    Activations Density 0.393%

    No Known Activations