© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11371
    Prev
    Next
    INDEX
    Explanations

    latex or other formula-like syntax, often with citations

    oai_token-act-pair · gemini-2.0-flash

    Code/mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    PropertyChanged
    -0.45
    une
    -0.45
     (
    -0.44
    _
    -0.41
    unes
    -0.41
     -
    -0.41
     root
    -0.40
    <eos>
    -0.40
     Il
    -0.40
    JMenuBar
    -0.40
    POSITIVE LOGITS
     Roskov
    1.05
    )";
    0.94
    verwijspagina
    0.85
    ">//
    0.82
    protoimpl
    0.81
    }],
    0.81
     '\\;'
    0.81
     Drapeau
    0.77
    Personendaten
    0.77
    tonode
    0.76
    Activations Density 5.089%

    No Known Activations