© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14060
    Prev
    Next
    INDEX
    Explanations

    strings of words that seem to be nonsensical and possibly from a different language.

    oai_token-act-pair · gemini-2.0-flash

    big

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Autoritní
    -0.63
     &
    -0.50
    webElementGuid
    -0.49
    struktion
    -0.49
    ituary
    -0.49
    fieldId
    -0.49
    ოლი
    -0.48
     Hinsicht
    -0.47
     AspNetCore
    -0.47
    cheme
    -0.47
    POSITIVE LOGITS
    ôtel
    0.52
     pymongo
    0.50
     betweenstory
    0.49
     skippy
    0.48
    шкан
    0.48
    .*")]
    0.47
    PerformLayout
    0.47
    atang
    0.46
     Тя
    0.45
    ++]=
    0.45
    Activations Density 7.878%

    No Known Activations