© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    numbers followed or preceded by certain letters

    oai_token-act-pair · gemini-2.0-flash

    File sizes and memory

    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
     byte
    -1.26
     bytes
    -1.23
    Byte
    -1.20
    bytes
    -1.18
    byte
    -1.14
    Bytes
    -1.13
     Byte
    -1.13
     Bytes
    -1.12
    BYTES
    -0.99
    字节
    -0.98
    POSITIVE LOGITS
     noDo
    0.48
    انيف
    0.48
    Personendaten
    0.47
    arschijnlijk
    0.46
    kadang
    0.46
    jmniej
    0.46
     Ko
    0.46
     Iro
    0.45
    ]")]
    0.45
     سبورت
    0.45
    Activations Density 3.591%

    No Known Activations