© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9987
    Prev
    Next
    INDEX
    Explanations

    the word 'state' used in a physical or medical context

    oai_token-act-pair · gemini-2.0-flash

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     included
    -0.50
    fortawesome
    -0.47
     statewide
    -0.47
    řeb
    -0.45
     State
    -0.45
    两次
    -0.44
    numer
    -0.44
    kém
    -0.44
    namentales
    -0.43
    ticularly
    -0.43
    POSITIVE LOGITS
    下载附件
    0.78
    parsedMessage
    0.77
    IsMutable
    0.67
    SharedDtor
    0.65
    oredCriteria
    0.63
    MergeFrom
    0.63
     EPISODE
    0.63
    yntaxException
    0.62
     ISNI
    0.62
     Mechanisms
    0.62
    Activations Density 0.353%

    No Known Activations