© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    line breaks including indentations in the form of spaces and consecutive numbers

    oai_token-act-pair · gemini-2.0-flash

    Technical documents

    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
     Monfieur
    -0.72
     Anſ
    -0.69
    ſelf
    -0.69
     Majefty
    -0.69
     doubtnut
    -0.68
     Arquivado
    -0.66
     pleaſure
    -0.66
    MENAFN
    -0.65
    Читати
    -0.64
     Efq
    -0.63
    POSITIVE LOGITS
    1.80
    ↵
    1.48
     \\
    1.08
    .

    1.02
    </h3>
    0.95
    )

    0.94
    )");
    0.89
     ***!
    0.89
    !

    0.88
    ]");
    0.88
    Activations Density 2.239%
    No Known Activations