© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14524
    Prev
    Next
    INDEX
    Explanations

    the letter "d" and the word "be".

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     برانيه
    -0.48
     néer
    -0.44
     contrats
    -0.43
     previs
    -0.39
    zdo
    -0.38
     armé
    -0.38
     aveug
    -0.38
     énorm
    -0.37
    perror
    -0.37
     contratto
    -0.37
    POSITIVE LOGITS
    StoryboardSegue
    0.90
     doInBackground
    0.86
     للمعارف
    0.86
    MigrationBuilder
    0.85
     ویکی‌پدیا
    0.84
     متعلقه
    0.82
    makeConstraints
    0.78
     disambiguazione
    0.77
    argout
    0.76
    AutoresizingMask
    0.76
    Activations Density 2.561%

    No Known Activations