© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1860
    Prev
    Next
    INDEX
    Explanations

    a series of uppercase letters, some mixed with numbers, that may represent a code or identifier.

    oai_token-act-pair · gemini-2.0-flash

    Genetic sequences and mutations

    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
    цездатний
    -0.76
    ^(@)
    -0.70
    <bos>
    -0.70
     betweenstory
    -0.68
     يتيمه
    -0.66
    )";
    
    -0.60
     Efq
    -0.59
     Jefus
    -0.59
    Бележки
    -0.59
     doubtnut
    -0.58
    POSITIVE LOGITS
    \\
    0.60
     <<<<<<<<<<<<<<
    0.56
    <b>
    0.56
     ag
    0.55
     ge
    0.54
    kev
    0.54
     kem
    0.54
     pem
    0.52
    iella
    0.52
    ῆ
    0.52
    Activations Density 9.910%

    No Known Activations