© 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. 5293
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications for products, appearing to focus on measurements and construction.

    oai_token-act-pair · gemini-2.0-flash

    Combining parts/duality

    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
    Hentet
    -0.79
     kaarangay
    -0.69
    ⓧ
    -0.68
    seamnă
    -0.61
    })));
    -0.59
    BorderFactory
    -0.55
     transfieras
    -0.55
    (")");
    -0.54
     scientifiques
    -0.52
    rxjs
    -0.51
    POSITIVE LOGITS
     tone
    0.56
     Zone
    0.51
     Tone
    0.47
     core
    0.47
    PIECE
    0.46
    Tone
    0.45
     Lik
    0.45
    ímetros
    0.45
     zone
    0.45
     متعلقه
    0.45
    Activations Density 0.970%

    No Known Activations