© 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. 12543
    Prev
    Next
    INDEX
    Explanations

    Russian words, especially those related to shopping or website elements

    oai_token-act-pair · gemini-2.0-flash

    special

    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
     Мексичка
    -0.62
     Walkover
    -0.59
     resourceCulture
    -0.59
     makeStyles
    -0.55
     noqa
    -0.55
    numerusform
    -0.54
     للمعارف
    -0.54
    NCS
    -0.54
     NCS
    -0.54
     Wikimedijinoj
    -0.53
    POSITIVE LOGITS
     special
    0.56
     Special
    0.54
    ://$
    0.51
    lipop
    0.49
     SPECIAL
    0.48
     Gedichte
    0.47
     literaria
    0.46
    Special
    0.46
     conflits
    0.45
    special
    0.45
    Activations Density 0.069%

    No Known Activations