© 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. 10873
    Prev
    Next
    INDEX
    Explanations

    words related to taking action or expressing desires

    oai_token-act-pair · gemini-2.0-flash

    software questions

    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
    ]").
    -0.59
    "]).
    -0.56
    ).__
    -0.55
    ())).
    -0.54
    Hentet
    -0.53
    ']).
    -0.50
    iocene
    -0.48
     незавершена
    -0.48
     domes
    -0.48
     depositphotos
    -0.47
    POSITIVE LOGITS
    Personensuche
    0.83
     دیکھیے
    0.60
     pracovní
    0.56
    WindowConstants
    0.54
    lccn
    0.54
     necessárias
    0.53
    weh
    0.53
     canlynol
    0.52
     bulunabilir
    0.52
     intent
    0.52
    Activations Density 11.318%

    No Known Activations