© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12622
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to loops, arrays, and data structures.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Приступљено
    -0.63
    expandindo
    -0.61
    :].
    -0.57
    iyaki
    -0.55
    awtextra
    -0.53
    ]';
    -0.50
    garder
    -0.47
     numerus
    -0.47
    InSection
    -0.47
    ]--;
    -0.47
    POSITIVE LOGITS
     company
    0.56
    ()(
    0.50
     Trident
    0.50
     DbSet
    0.49
    company
    0.49
    (--
    0.49
    ilan
    0.48
    ecore
    0.47
    Étymologie
    0.46
    éo
    0.46
    Activations Density 55.385%

    No Known Activations