© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13173
    Prev
    Next
    INDEX
    Explanations

    java code

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    MemoryWarning
    -0.92
    RUnlock
    -0.75
    featureID
    -0.75
     незавершена
    -0.73
    __*/
    -0.71
    MLLoader
    -0.68
     autorytatywna
    -0.67
    endphp
    -0.65
    󠁢
    -0.64
    </thead>
    -0.63
    POSITIVE LOGITS
    WriteTagHelper
    0.60
    millan
    0.50
    <bos>
    0.49
     considération
    0.42
    Дереккөздер
    0.42
    레이
    0.42
    ]").
    0.40
    createStatement
    0.40
     दिया
    0.39
     quei
    0.39
    Activations Density 2.393%

    No Known Activations