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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15897
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly disparate tokens, including math symbols, illness related words, and names

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
    MigrationBuilder
    -0.48
     esternos
    -0.43
    ftagPool
    -0.41
     getItemId
    -0.40
    فحة
    -0.39
     Chwiliwch
    -0.37
    astéroïdes
    -0.36
     للاسماء
    -0.35
    СТВА
    -0.35
     GenerationType
    -0.34
    POSITIVE LOGITS
    NE
    0.96
    NI
    0.94
     NE
    0.93
     NN
    0.92
     NU
    0.92
    NIC
    0.91
    NEL
    0.89
    nit
    0.88
    Ni
    0.88
     NI
    0.88
    Activations Density 18.187%

    No Known Activations