© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11185
    Prev
    Next
    INDEX
    Explanations

    text using technical jargon related to sales and/or customer service

    oai_token-act-pair · gemini-2.0-flash

    Code, documentation, or technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AndEndTag
    -0.97
    Datuak
    -0.80
     насељу
    -0.75
    MemoryWarning
    -0.69
    ValueStyle
    -0.62
    Geplaatst
    -0.60
     kasarigan
    -0.59
    олові
    -0.58
    :✨
    -0.56
    argli
    -0.56
    POSITIVE LOGITS
    ')")
    0.49
    Odkazy
    0.49
     Jwt
    0.48
    Còn
    0.47
    felves
    0.45
    qxd
    0.45
    mặt
    0.44
     komment
    0.44
    plass
    0.44
    udadera
    0.43
    Activations Density 13.723%

    No Known Activations