© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10567
    Prev
    Next
    INDEX
    Explanations

    words relating to air conditioning and home appliance services

    oai_token-act-pair · gemini-2.0-flash

    air conditioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    chium
    -0.50
    Smash
    -0.50
     Smash
    -0.48
    fromnode
    -0.48
    apiVersion
    -0.47
    leroi
    -0.47
    RTLI
    -0.45
    mente
    -0.45
    йн
    -0.44
    bogen
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.73
    Cyfeiriadau
    0.70
    IndentedString
    0.69
     المعيارى
    0.67
     Италијани
    0.67
    addCriterion
    0.65
     виправивши
    0.63
    LookAnd
    0.63
    mphony
    0.62
    ")));
    0.61
    Activations Density 1.094%

    No Known Activations