© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11852
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, financial terms, positive sentiment, and also the word "every".

    oai_token-act-pair · gemini-2.0-flash

    code and technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     each
    -2.30
     Each
    -2.22
    Each
    -2.22
    each
    -2.08
     EACH
    -1.91
    EACH
    -1.90
    Chaque
    -1.74
     chaque
    -1.73
     Chaque
    -1.66
     fiecare
    -1.66
    POSITIVE LOGITS
    ]")]
    0.66
     ModelExpression
    0.63
    glEnd
    0.62
    GenerationType
    0.62
    setImageBitmap
    0.60
     <=",
    0.58
     UserDao
    0.57
    TagMode
    0.56
     alternatif
    0.55
     AppCompatTheme
    0.52
    Activations Density 2.733%

    No Known Activations