© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10962
    Prev
    Next
    INDEX
    Explanations

    the phrase "customer service" or related terms

    oai_token-act-pair · gemini-2.0-flash

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    UIControlState
    -0.73
     ostavi
    -0.72
    saraba
    -0.67
    +#+#
    -0.66
     يتيمه
    -0.64
    setupUi
    -0.58
     Audiodateien
    -0.57
    basicConfig
    -0.57
    الإنجليزية
    -0.56
     BoxFit
    -0.55
    POSITIVE LOGITS
    }';
    0.64
     lãng
    0.61
     энциклопедия
    0.61
    chiato
    0.60
    pters
    0.57
    gefü
    0.57
    enegro
    0.56
    CppMethod
    0.55
     отношение
    0.55
    bability
    0.54
    Activations Density 0.752%

    No Known Activations