© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5270
    Prev
    Next
    INDEX
    Explanations

    code snippets or URLs

    oai_token-act-pair · gemini-2.0-flash

    code/URLs/email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     سكانية
    -0.52
    FieldOffset
    -0.47
    idue
    -0.46
     Safran
    -0.43
     Cal
    -0.43
    elum
    -0.43
     El
    -0.42
    democratic
    -0.42
     Char
    -0.42
     aange
    -0.41
    POSITIVE LOGITS
    IndentedString
    0.90
    <bos>
    0.87
     Monfieur
    0.86
     Jefus
    0.84
     purpoſe
    0.79
     BoxFit
    0.77
     ſtate
    0.76
     Anſ
    0.75
     myſelf
    0.73
     itſelf
    0.71
    Activations Density 2.351%

    No Known Activations