© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10919
    Prev
    Next
    INDEX
    Explanations

    words suggesting uncertainty, questions, and possibilities

    oai_token-act-pair · gemini-2.0-flash

    Modality/Future Tense

    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
    xial
    -0.51
     الحره
    -0.47
    badlogic
    -0.44
    CppMethod
    -0.40
     policiales
    -0.39
    billon
    -0.39
     cơn
    -0.39
     TR
    -0.38
    Scénario
    -0.38
    Roc
    -0.37
    POSITIVE LOGITS
    DebuggerNonUser
    0.71
    parsedMessage
    0.65
    arraycopy
    0.65
    protoimpl
    0.61
    Искәрмәләр
    0.60
     Citation
    0.59
    exitRule
    0.59
     intermédiaire
    0.57
     AssemblyVersion
    0.57
    endphp
    0.57
    Activations Density 31.047%

    No Known Activations