© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 714
    Prev
    Next
    INDEX
    Explanations

    words written in Russian or that look like Russian words transliterated into English.

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    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
     myſelf
    -1.05
     itſelf
    -0.94
     themſelves
    -0.88
     himſelf
    -0.83
     purpoſe
    -0.81
     whoſe
    -0.81
     pleaſure
    -0.81
     ſhe
    -0.81
     raiſ
    -0.79
     ſtate
    -0.79
    POSITIVE LOGITS
     autorytatywna
    0.53
    RegressionTest
    0.52
    stridium
    0.50
    iecie
    0.48
    argli
    0.47
    __*/
    0.46
     Vikipedi
    0.46
     rembour
    0.45
    Източници
    0.44
    Datuak
    0.44
    Activations Density 0.409%

    No Known Activations