© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6103
    Prev
    Next
    INDEX
    Explanations

    the word 'Open', often followed by 'Compute'

    oai_token-act-pair · gemini-2.0-flash

    Open

    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
     Paglinawan
    -0.84
     @}
    -0.75
    invokeLater
    -0.74
     Roskov
    -0.74
    EndGlobalSection
    -0.67
    SequentialGroup
    -0.66
    ^(@)
    -0.65
     صوتيه
    -0.65
    Manbalar
    -0.63
    httphttps
    -0.63
    POSITIVE LOGITS
    tiana
    0.48
     mattina
    0.46
    WidgetItem
    0.44
    方で
    0.44
    embedded
    0.44
     préc
    0.43
    ซ
    0.43
     attacco
    0.43
     aéri
    0.42
     sement
    0.42
    Activations Density 1.102%

    No Known Activations