© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3351
    Prev
    Next
    INDEX
    Explanations

    snippets of Portuguese code

    oai_token-act-pair · gemini-2.0-flash

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -1.46
     fubject
    -1.33
     myſelf
    -1.31
     Efq
    -1.28
     Majefty
    -1.27
     poffible
    -1.24
     Jefus
    -1.21
     Cæsar
    -1.18
     Shakspeare
    -1.16
     themſelves
    -1.15
    POSITIVE LOGITS
     and
    1.45
     et
    0.96
     AND
    0.94
     &&
    0.91
     und
    0.90
     và
    0.89
     och
    0.89
     And
    0.88
     и
    0.88
    and
    0.83
    Activations Density 0.031%

    No Known Activations