© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1663
    Prev
    Next
    INDEX
    Explanations

    content related to flower delivery services

    oai_token-act-pair · gemini-2.0-flash

    requests, offers, communication. I picked this because many texts include things that you could order, or requests for information, or other business related activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SourceChecksum
    -0.81
    setVerticalGroup
    -0.68
     kasarigan
    -0.64
    
    -0.64
    StructEnd
    -0.62
     nakalista
    -0.62
    SequentialGroup
    -0.60
    الحياه
    -0.59
    adpleegd
    -0.56
    bayan
    -0.56
    POSITIVE LOGITS
    eseorang
    0.57
    утбо
    0.56
     uLocal
    0.53
     don
    0.47
    writeHead
    0.46
    )))));
    0.46
    CanBe
    0.46
     Offisielt
    0.45
    ưng
    0.45
    Pul
    0.44
    Activations Density 0.847%

    No Known Activations