© 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. 2160
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to communicate, notify, or train others

    oai_token-act-pair · gemini-2.0-flash

    legal/bureaucratic language

    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
     $[-
    -0.57
    sticks
    -0.56
    terday
    -0.55
     للمعارف
    -0.55
    binaan
    -0.54
    watching
    -0.52
     endfor
    -0.51
    ToProps
    -0.51
     $]$
    -0.51
     niets
    -0.50
    POSITIVE LOGITS
     Telling
    0.85
     TELL
    0.81
     tell
    0.81
     Tell
    0.80
     Tells
    0.79
     Told
    0.79
    Tell
    0.76
    Telling
    0.76
     tells
    0.75
    Told
    0.75
    Activations Density 1.016%

    No Known Activations