© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16230
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to customer support and order fulfillment

    oai_token-act-pair · gemini-2.0-flash

    please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     itſelf
    -0.75
     Houſe
    -0.73
     Reſ
    -0.69
     houſe
    -0.67
     uſed
    -0.66
     Monfieur
    -0.66
     himſelf
    -0.66
     themſelves
    -0.65
    neſs
    -0.64
     raiſ
    -0.63
    POSITIVE LOGITS
    <?
    0.50
    новниш
    0.44
    вей
    0.41
     Walkover
    0.40
     समीक्षाएं
    0.40
    bel
    0.39
    arj
    0.39
    терна
    0.39
    zlich
    0.39
    ars
    0.38
    Activations Density 0.896%

    No Known Activations