© 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. 15491
    Prev
    Next
    INDEX
    Explanations

    strings of letters that appear to be parts of names or words, often with accompanying numbers

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     متعلقه
    -0.62
    rungsseite
    -0.60
    awtextra
    -0.59
     صوتيه
    -0.59
     OFDb
    -0.58
    UnsafeEnabled
    -0.57
     Walkover
    -0.56
    ImageContext
    -0.56
    Personensuche
    -0.56
     kip
    -0.55
    POSITIVE LOGITS
     megfe
    0.88
     történ
    0.85
     avulla
    0.84
     különböz
    0.81
     aikana
    0.81
     előtt
    0.80
     nélk
    0.79
    nál
    0.79
     vastaan
    0.77
    ltä
    0.77
    Activations Density 1.895%

    No Known Activations